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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hentet
    -0.95
    MLLoader
    -0.86
     seguinte
    -0.70
     صوتيه
    -0.69
     Autorizaciones
    -0.64
     فريبيس
    -0.63
     Bourgoin
    -0.61
    )|^{
    -0.60
    Síguenos
    -0.59
    MVH
    -0.58
    POSITIVE LOGITS
    ParallelGroup
    0.63
    at
    0.62
     كومونز
    0.61
    Див
    0.60
    aka
    0.58
     ostavi
    0.56
    twimg
    0.56
    WillAppear
    0.56
    not
    0.55
    ExtendWith
    0.55
    Act Density 0.659%

    No Known Activations