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

    Neuronpedia

    INDEX
    Explanations

    references to surveys and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usalem
    -0.15
    aura
    -0.15
    ruba
    -0.14
    tera
    -0.14
    ingly
    -0.14
    anni
    -0.14
     Kou
    -0.14
    .micro
    -0.14
    pone
    -0.14
    unist
    -0.13
    POSITIVE LOGITS
     SAMPLE
    0.16
    SAMPLE
    0.15
    ìĥ
    0.15
    adle
    0.14
     samples
    0.14
     Gamer
    0.14
    ATUS
    0.14
    edu
    0.13
     ìĥ
    0.13
    248
    0.13
    Act Density 0.020%

    No Known Activations