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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change has occurred or is occurring

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anymore," indicating a theme of change or cessation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erest
    -0.72
    tale
    -0.68
    ortment
    -0.67
    stood
    -0.66
    urer
    -0.65
    maximum
    -0.62
    yp
    -0.61
    ouri
    -0.60
    ffe
    -0.59
    erate
    -0.58
    POSITIVE LOGITS
    adays
    0.89
     than
    0.79
    iatus
    0.77
     ;)
    0.77
    nces
    0.77
     :-)
    0.73
    !!!!!
    0.71
     :)
    0.71
     :(
    0.68
     ðŁĻĤ
    0.68
    Act Density 0.023%

    No Known Activations