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

    Neuronpedia

    INDEX
    Explanations

    narratives of self-sacrifice and bravery

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     <=",
    -0.59
    ambito
    -0.55
    findpost
    -0.54
    ⓧ
    -0.53
     bienvenue
    -0.53
    intios
    -0.52
    untung
    -0.52
    そろそろ
    -0.51
     ExecuteAsync
    -0.51
    ative
    -0.50
    POSITIVE LOGITS
     sacrificing
    0.62
     selfless
    0.61
    batore
    0.59
    ">—
    0.56
     sacrificial
    0.54
     sacrifices
    0.52
    caring
    0.51
    getHours
    0.50
     sacrificio
    0.50
     nyingi
    0.50
    Act Density 0.197%

    No Known Activations