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

    Neuronpedia

    INDEX
    Explanations

    actions related to rescue or removal from danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lob
    -0.17
    voy
    -0.17
     vice
    -0.17
    aidu
    -0.16
     spot
    -0.15
     dr
    -0.14
    vice
    -0.14
    _CID
    -0.14
    vic
    -0.14
    ayette
    -0.14
    POSITIVE LOGITS
     away
    0.20
     alive
    0.18
    edException
    0.17
     götür
    0.16
    alive
    0.16
    移åĪ°
    0.15
    orris
    0.15
    aseline
    0.15
    LTR
    0.15
    ?type
    0.15
    Act Density 0.068%

    No Known Activations