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

    Neuronpedia

    INDEX
    Explanations

    instances of speaking or conversation-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    물
    -0.15
    rien
    -0.15
    plex
    -0.15
    igan
    -0.14
    ecycle
    -0.14
    ãģıãĤĵ
    -0.14
    acea
    -0.14
    aina
    -0.14
    bane
    -0.13
    aki
    -0.13
    POSITIVE LOGITS
    ÙĨÚ¯
    0.17
    erville
    0.16
     minded
    0.15
    reau
    0.15
    inded
    0.14
    -minded
    0.14
    çĶ²
    0.14
    neider
    0.14
    vens
    0.14
    peare
    0.14
    Act Density 0.047%

    No Known Activations