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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and interaction between individuals

    oai_token-act-pair · gpt-3.5-turbo

    indications of conversations or dialogue exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.80
    olated
    -0.74
    mone
    -0.69
    arde
    -0.69
    licts
    -0.68
    rolet
    -0.66
    İĭ
    -0.66
    MpServer
    -0.64
    inent
    -0.63
     Shadows
    -0.62
    POSITIVE LOGITS
     reply
    1.81
     replies
    1.68
     replied
    1.66
     responded
    1.64
     answer
    1.61
     answered
    1.55
     response
    1.55
     responds
    1.49
    response
    1.45
     responses
    1.43
    Act Density 1.278%

    No Known Activations