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

    Neuronpedia

    INDEX
    Explanations

    words related to envelopes and development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to development and preservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.75
     antid
    -0.72
     misdem
    -0.71
     dramas
    -0.70
     convictions
    -0.70
     barg
    -0.67
     breakout
    -0.65
    isd
    -0.63
    ãĥ¢
    -0.63
    76561
    -0.62
    POSITIVE LOGITS
    ritic
    0.84
    ript
    0.81
    itized
    0.81
     Goff
    0.78
    ancy
    0.78
    riter
    0.76
    ensation
    0.76
    alty
    0.76
    hetically
    0.75
    tin
    0.75
    Act Density 0.030%

    No Known Activations