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

    Neuronpedia

    INDEX
    Explanations

    instances of agreement and refusal in interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é»
    -0.15
    opoulos
    -0.15
    oui
    -0.15
    uien
    -0.14
    abar
    -0.14
    éri
    -0.14
     Incident
    -0.14
    ingroup
    -0.14
    _soft
    -0.13
     Bolton
    -0.13
    POSITIVE LOGITS
    asca
    0.18
     reply
    0.17
    rames
    0.16
    rott
    0.15
     replied
    0.15
    piler
    0.15
    .fn
    0.15
     suit
    0.15
    Hdr
    0.14
    ormsg
    0.14
    Act Density 0.121%

    No Known Activations