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

    Neuronpedia

    INDEX
    Explanations

    concepts related to reciprocity and responses in interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errick
    -0.19
    ubre
    -0.16
    apel
    -0.15
    achuset
    -0.15
     actionTypes
    -0.15
    éĽĦ
    -0.15
     ÎķÎł
    -0.14
    ephy
    -0.14
    çīĮ
    -0.14
    ahren
    -0.14
    POSITIVE LOGITS
    izzo
    0.15
    croft
    0.15
    usta
    0.15
    .iv
    0.14
     carn
    0.14
    :return
    0.14
    ίÏĥÏī
    0.14
    ero
    0.14
    TY
    0.13
    raries
    0.13
    Act Density 0.113%

    No Known Activations