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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social or psychological actions and states

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating social dynamics and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referring
    -0.56
     Sloan
    -0.54
    orsi
    -0.53
    ère
    -0.53
     Citation
    -0.52
     Bearing
    -0.51
     hemor
    -0.50
     2002
    -0.50
     1902
    -0.50
     demonstrating
    -0.50
    POSITIVE LOGITS
    iped
    0.61
    natureconservancy
    0.59
    olitical
    0.57
    aband
    0.57
    endas
    0.57
    rows
    0.55
    blers
    0.54
    thood
    0.54
    hetics
    0.53
    aughs
    0.52
    Act Density 1.263%

    No Known Activations