Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to computer software or technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "biv", which appears to be related to a specific topic or item, likely indicating a focus on certain types of products or brands, particularly in a critical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     secrecy
    -0.71
    --------------------------------------------------------
    -0.70
     rule
    -0.61
     mount
    -0.61
     poppy
    -0.60
     unregulated
    -0.59
    Ħ¢
    -0.59
    xon
    -0.59
     overpower
    -0.59
     Carly
    -0.58
    POSITIVE LOGITS
    isions
    1.07
    olution
    1.04
    iew
    1.02
    entric
    1.01
    orst
    0.99
    ascular
    0.98
    ision
    0.97
    irus
    0.97
    ocally
    0.95
    isible
    0.94
    Act Density 0.028%

    No Known Activations