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

    Neuronpedia

    INDEX
    Explanations

    instances of quantified amounts and values in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akat
    -0.18
    resco
    -0.15
     sonu
    -0.15
    ÙĴÙĨ
    -0.14
    ouz
    -0.14
    ewn
    -0.14
    ɵ
    -0.14
    addons
    -0.14
    ikki
    -0.14
    enu
    -0.14
    POSITIVE LOGITS
     similarly
    0.16
    uner
    0.15
    cak
    0.15
    Ñĭл
    0.14
    Binder
    0.14
    ÑĪин
    0.14
    thouse
    0.13
    sv
    0.13
    lland
    0.13
     Nimbus
    0.13
    Act Density 0.509%

    No Known Activations