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

    Neuronpedia

    INDEX
    Explanations

    words related to conditional expressions and possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iculos
    -0.16
    trail
    -0.16
    _CN
    -0.16
    iddet
    -0.15
    ilver
    -0.15
    gaben
    -0.15
    ël
    -0.15
    ixo
    -0.15
    ibase
    -0.15
    tracer
    -0.15
    POSITIVE LOGITS
    730
    0.17
    shed
    0.17
    722
    0.17
     è¡ĮæĶ¿
    0.16
     Perkins
    0.16
    ior
    0.16
    406
    0.16
     Tib
    0.16
     experimental
    0.16
    ced
    0.15
    Act Density 0.005%

    No Known Activations