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

    Neuronpedia

    INDEX
    Explanations

    references to specific quantities and settings related to measurements or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -INF
    -0.17
     *)((
    -0.15
    olumn
    -0.15
    artz
    -0.15
    hiba
    -0.14
    iddet
    -0.14
     Yong
    -0.14
    ycop
    -0.14
     Drake
    -0.14
    .opend
    -0.14
    POSITIVE LOGITS
    ạn
    0.17
    etch
    0.17
    tober
    0.17
    aram
    0.16
    ogen
    0.16
    립
    0.16
    maz
    0.15
    ello
    0.14
    igm
    0.14
    ikon
    0.14
    Act Density 0.041%

    No Known Activations