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

    Neuronpedia

    INDEX
    Explanations

    terms associated with conflict and tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icus
    -0.78
    EVA
    -0.71
    ural
    -0.69
    aca
    -0.66
    esis
    -0.64
    ogo
    -0.63
    LY
    -0.61
    aneous
    -0.61
    DOS
    -0.61
    rodu
    -0.60
    POSITIVE LOGITS
     spiked
    0.81
     persist
    0.79
     snowball
    0.77
     gripped
    0.76
     soared
    0.76
     intensified
    0.74
     abound
    0.73
     swirl
    0.73
     erupted
    0.72
     deep
    0.71
    Act Density 0.370%

    No Known Activations