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

    Neuronpedia

    INDEX
    Explanations

    expressions related to systematic analysis and routine processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Branch
    -0.23
    olini
    -0.18
    branches
    -0.18
     تض
    -0.15
    branch
    -0.15
    Branch
    -0.15
    بÙĪ
    -0.15
     Bucket
    -0.15
    broker
    -0.14
     seedu
    -0.14
    POSITIVE LOGITS
     basis
    0.59
    basis
    0.45
     bases
    0.45
     Basis
    0.42
     bais
    0.35
    asis
    0.33
    _basis
    0.33
     BASIS
    0.31
    åŁºç¡Ģ
    0.31
     оÑģнове
    0.29
    Act Density 0.022%

    No Known Activations