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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurement and classification within various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _SYM
    -0.16
    marshaller
    -0.15
    ddy
    -0.15
    عاÙĨ
    -0.15
    .sequence
    -0.14
    SCII
    -0.14
    oS
    -0.14
    -translate
    -0.14
    _REUSE
    -0.14
    عب
    -0.13
    POSITIVE LOGITS
    chez
    0.15
    acob
    0.15
    igan
    0.15
    igans
    0.14
    воз
    0.14
    ivate
    0.14
    _TI
    0.13
    alice
    0.13
    ĶåĽŀ
    0.13
    keit
    0.13
    Act Density 0.062%

    No Known Activations