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

    Neuronpedia

    INDEX
    Explanations

    terms associated with classification, categorization, or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    ZN
    -0.16
    antry
    -0.16
    schemas
    -0.16
    atra
    -0.16
    ouchers
    -0.15
    eyer
    -0.15
     Stub
    -0.15
    ertino
    -0.15
    è¥
    -0.15
    POSITIVE LOGITS
    <boost
    0.14
    ivo
    0.14
    wick
    0.14
     actionable
    0.14
     Semi
    0.14
    _INTR
    0.14
    åħ
    0.13
     Ñĥгод
    0.13
    erate
    0.13
     cracks
    0.13
    Act Density 0.013%

    No Known Activations