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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or states involving companionship and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alth
    -0.16
    Ïģαν
    -0.16
    olini
    -0.15
    orp
    -0.15
     Bolton
    -0.14
    peq
    -0.14
    ylon
    -0.14
    god
    -0.14
    chten
    -0.14
     Bol
    -0.14
    POSITIVE LOGITS
     vo
    0.21
     prest
    0.18
    vo
    0.17
     instant
    0.16
    'll
    0.15
     instantly
    0.15
    obo
    0.15
    transforms
    0.15
    ivic
    0.14
     viol
    0.14
    Act Density 0.107%

    No Known Activations