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

    Neuronpedia

    INDEX
    Explanations

    phrases related to using technology or tools

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the action of utilizing a specific tool or method

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uberty
    -0.76
    hound
    -0.75
    nesty
    -0.72
    cffffcc
    -0.72
    owship
    -0.70
    si
    -0.69
    merce
    -0.68
    hood
    -0.68
    naire
    -0.68
    mobi
    -0.67
    POSITIVE LOGITS
    FUL
    0.74
     sparing
    0.74
     borrowed
    0.71
     scissors
    0.69
     shortcuts
    0.68
     techniques
    0.67
     contacts
    0.67
     coupons
    0.67
    fully
    0.66
     condoms
    0.66
    Act Density 0.055%

    No Known Activations