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

    Neuronpedia

    INDEX
    Explanations

    concepts related to specific conditions or criteria in studies or experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "only" or "to"

    np_acts-logits-general · gemini-2.0-flash

    specifies "only"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    клопе
    -0.61
    ValueStyle
    -0.60
     altrett
    -0.58
     spéciaux
    -0.57
     getItemId
    -0.56
     exemplo
    -0.56
    WriteLiteral
    -0.56
     Feynman
    -0.56
     illustre
    -0.55
     bushels
    -0.55
    POSITIVE LOGITS
     single
    0.81
     male
    0.79
     non
    0.76
     TextAppearance
    0.68
     males
    0.68
     older
    0.66
     female
    0.66
     private
    0.66
     pure
    0.64
    single
    0.62
    Act Density 1.078%

    No Known Activations