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

    Neuronpedia

    INDEX
    Explanations

    be verbs and their various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.73
     ſever
    -0.70
    enumi
    -0.69
     Nero
    -0.68
     Medea
    -0.68
    globin
    -0.67
     poto
    -0.66
     epistle
    -0.65
     Neum
    -0.65
     Quail
    -0.65
    POSITIVE LOGITS
     the
    0.83
     that
    0.72
    :
    0.70
    matchCondition
    0.61
     our
    0.58
    principalColumn
    0.58
    @",
    0.57
    elsif
    0.56
     a
    0.55
    fileID
    0.55
    Act Density 0.324%

    No Known Activations