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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and their relationships in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omitempty
    -0.60
     propOrder
    -0.55
     salomon
    -0.53
     malic
    -0.53
    óng
    -0.53
    arounds
    -0.52
    standers
    -0.51
     Morm
    -0.51
     CanadaChoose
    -0.50
     ligaments
    -0.48
    POSITIVE LOGITS
     فريبيس
    0.79
     lenker
    0.67
     صوتيه
    0.63
     nature
    0.63
     textStatus
    0.60
    mű
    0.59
    بوابة
    0.59
     }^{[
    0.59
    openqa
    0.59
    saraba
    0.58
    Act Density 0.450%

    No Known Activations