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

    Neuronpedia

    INDEX
    Explanations

    mentions of booths and their associated features or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esub
    -0.17
    hoot
    -0.15
    Äł
    -0.15
    rrha
    -0.15
    .qq
    -0.15
    ISA
    -0.14
    imiento
    -0.14
    зн
    -0.14
    itably
    -0.13
    <quote
    -0.13
    POSITIVE LOGITS
    igram
    0.17
    /train
    0.15
    ilm
    0.14
    GRESS
    0.14
    orgen
    0.14
     setPosition
    0.14
    805
    0.14
    orton
    0.14
     Henrik
    0.13
     entrance
    0.13
    Act Density 0.002%

    No Known Activations