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

    Neuronpedia

    INDEX
    Explanations

    relationships between people and emotions

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UCK
    -0.75
     Nanto
    -0.73
    DEN
    -0.67
    rick
    -0.67
     convergence
    -0.67
    ories
    -0.64
    OOK
    -0.63
    DOS
    -0.61
    lav
    -0.61
    CONCLUS
    -0.61
    POSITIVE LOGITS
     else
    0.94
    soever
    0.92
     whom
    0.88
     inappropriately
    0.85
    selves
    0.84
     who
    0.79
     anonymously
    0.78
     behaving
    0.78
    else
    0.73
    folk
    0.72
    Act Density 0.218%

    No Known Activations