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

    Neuronpedia

    INDEX
    Explanations

    words related to service or physical states of being

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concepts of securing and ensuring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.69
    itta
    -0.68
    alter
    -0.63
     Tsukuyomi
    -0.62
    BB
    -0.60
     SQ
    -0.59
    achi
    -0.58
    Jump
    -0.58
    govtrack
    -0.58
    alog
    -0.58
    POSITIVE LOGITS
     embr
    0.71
    wolves
    0.68
    culosis
    0.68
    urances
    0.68
     Brach
    0.68
    pring
    0.67
    iences
    0.66
    ures
    0.65
    nikov
    0.64
    izational
    0.63
    Act Density 0.081%

    No Known Activations