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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or qualities related to a person or group

    oai_token-act-pair · gpt-3.5-turbo

    words associated with cooperation, social dynamics, and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guan
    -0.71
    htaking
    -0.68
    anton
    -0.67
    ©¶æ
    -0.65
     himself
    -0.63
    hander
    -0.61
     Himself
    -0.60
    cussion
    -0.60
     extrad
    -0.59
     Brady
    -0.59
    POSITIVE LOGITS
     selves
    1.58
     counterparts
    1.38
     brethren
    0.94
    selves
    0.88
     asses
    0.86
     careers
    0.81
     tongues
    0.78
     identities
    0.77
     histories
    0.77
     equivalents
    0.75
    Act Density 0.474%

    No Known Activations