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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurement and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussed
    -0.16
    reon
    -0.16
    elle
    -0.15
    oeff
    -0.15
    ohn
    -0.14
    swer
    -0.14
    è¬
    -0.14
     otherwise
    -0.14
    relevant
    -0.14
    edx
    -0.13
    POSITIVE LOGITS
    ATAB
    0.15
    951
    0.15
    ais
    0.15
    asn
    0.14
    anka
    0.14
    idth
    0.14
    punk
    0.14
    eger
    0.14
    amas
    0.14
    itra
    0.13
    Act Density 0.010%

    No Known Activations