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

    Neuronpedia

    INDEX
    Explanations

    terms related to corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anxiety
    -0.71
    uberty
    -0.68
    ãĥ¼ãĥ³
    -0.67
    zig
    -0.67
    gain
    -0.67
    ovember
    -0.66
    ãĤ¤ãĥĪ
    -0.65
    ches
    -0.64
    ynthesis
    -0.64
    agine
    -0.63
    POSITIVE LOGITS
    ible
    1.13
    ions
    1.11
    ibly
    0.99
    ly
    0.95
    ingly
    0.90
    ulent
    0.90
    ing
    0.89
    nesses
    0.86
    ive
    0.83
    ibility
    0.82
    Act Density 0.015%

    No Known Activations