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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hidden or underlying problems or situations, often with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant issues or problems that may go unnoticed or unaddressed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illions
    -0.73
     realise
    -0.67
    oubted
    -0.63
    ventus
    -0.62
    inav
    -0.62
    estern
    -0.61
    itialized
    -0.59
     Honour
    -0.58
     proverb
    -0.58
    gently
    -0.57
    POSITIVE LOGITS
    .
    1.11
    .[
    0.85
    .(
    0.85
    .*
    0.82
    ."
    0.81
    .:
    0.80
    .'
    0.80
    .''.
    0.80
    .?
    0.78
     of
    0.78
    Act Density 0.947%

    No Known Activations