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

    Neuronpedia

    INDEX
    Explanations

    words related to negative events or situations, particularly ones involving harm or loss

    oai_token-act-pair · gpt-3.5-turbo

    terms related to death and significant departures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.74
    enegger
    -0.73
    Cola
    -0.72
    cale
    -0.72
    isine
    -0.69
    zzy
    -0.67
    igmatic
    -0.63
    ingo
    -0.63
    ocaly
    -0.63
    overe
    -0.62
    POSITIVE LOGITS
     of
    0.94
     thereof
    0.92
     OF
    0.66
     Flavoring
    0.65
     deadline
    0.61
    lights
    0.60
    switch
    0.60
     portion
    0.59
     shuffle
    0.59
    ritz
    0.58
    Act Density 0.198%

    No Known Activations