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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong opinions and evaluations about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prot
    -0.15
    лан
    -0.14
    isons
    -0.14
    umen
    -0.14
     Hudson
    -0.13
    usalem
    -0.13
    ueva
    -0.13
     Caldwell
    -0.13
    akin
    -0.13
    prit
    -0.13
    POSITIVE LOGITS
    imdi
    0.16
    anke
    0.15
    /vnd
    0.14
    tu
    0.14
    lund
    0.14
    akit
    0.14
    scribe
    0.14
    oriously
    0.13
    å§
    0.13
    .escape
    0.13
    Act Density 0.729%

    No Known Activations