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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or transition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the cessation of a state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.80
    osite
    -0.74
     opposite
    -0.71
     Enhancement
    -0.69
     Colour
    -0.67
    NG
    -0.66
    achev
    -0.65
    phen
    -0.64
    EStream
    -0.63
    imov
    -0.63
    POSITIVE LOGITS
     tolerate
    0.77
     tolerated
    0.77
    adays
    0.76
     bothering
    0.74
     residing
    0.71
     relying
    0.71
     confined
    0.71
     exists
    0.71
     obsolete
    0.71
     wedd
    0.70
    Act Density 0.048%

    No Known Activations