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

    Neuronpedia

    INDEX
    Explanations

    instances of formal announcements or notices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rose
    -0.18
    amespace
    -0.17
    SSIP
    -0.16
    sWith
    -0.15
    istry
    -0.15
    osate
    -0.14
    uploads
    -0.14
    alfa
    -0.14
    ätze
    -0.14
    notify
    -0.14
    POSITIVE LOGITS
    ably
    0.30
    ering
    0.19
    ously
    0.19
    abl
    0.19
    able
    0.18
     Undefined
    0.18
    lessly
    0.17
    ables
    0.17
    ances
    0.16
    full
    0.16
    Act Density 0.017%

    No Known Activations