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

    Neuronpedia

    INDEX
    Explanations

    references to coaching and coaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLY
    -0.15
    isle
    -0.15
    uously
    -0.15
    ously
    -0.15
    aires
    -0.15
    ầu
    -0.15
    phant
    -0.15
    al
    -0.14
    oids
    -0.14
    /div
    -0.14
    POSITIVE LOGITS
    (es
    0.28
    ella
    0.23
    erman
    0.20
    mans
    0.19
    man
    0.18
    yard
    0.17
    elling
    0.17
    surf
    0.17
    /co
    0.16
    eron
    0.16
    Act Density 0.022%

    No Known Activations