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

    Neuronpedia

    INDEX
    Explanations

    key phrases and concepts often related to documentation and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lla
    -0.17
    wit
    -0.16
    구
    -0.16
    imax
    -0.15
     Wal
    -0.15
    aney
    -0.15
    Wal
    -0.14
     maximal
    -0.14
    ãģĿ
    -0.14
    prit
    -0.14
    POSITIVE LOGITS
     Psalm
    0.15
    ml
    0.15
     fl
    0.15
     gul
    0.15
     arm
    0.14
    ulan
    0.14
    GOR
    0.14
     Uph
    0.14
     Arm
    0.14
     Playstation
    0.14
    Act Density 0.020%

    No Known Activations