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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their associated information

    oai_token-act-pair · gpt-3.5-turbo

    parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retard
    -0.84
     parity
    -0.79
     spir
    -0.78
     entitle
    -0.77
     versa
    -0.73
     lull
    -0.72
     commonplace
    -0.72
     nitrogen
    -0.71
     depress
    -0.70
     automatically
    -0.70
    POSITIVE LOGITS
    pictured
    1.46
    formerly
    1.34
    sic
    1.31
    aka
    1.25
    who
    1.19
    ?)
    1.15
    via
    1.13
    also
    1.12
    whose
    1.12
    pron
    1.10
    Act Density 0.135%

    No Known Activations