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

    Neuronpedia

    INDEX
    Explanations

    references to tragic events and personal harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agora
    -0.51
    quias
    -0.49
     constant
    -0.49
    constant
    -0.46
    newBuilder
    -0.44
    כשיו
    -0.44
    urier
    -0.44
     now
    -0.44
    THRO
    -0.44
    навли
    -0.44
    POSITIVE LOGITS
    UrlResolution
    0.75
    UnknownFields
    0.67
     Efq
    0.66
     AppColors
    0.63
     itſelf
    0.63
    ViewFeatures
    0.62
     électro
    0.59
     diſt
    0.59
     ſtate
    0.59
    évaluateur
    0.58
    Act Density 0.319%

    No Known Activations