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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Sharon" and "Schwartz."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ttle
    -0.89
    ntil
    -0.85
    cci
    -0.75
    ¥
    -0.75
    ¤
    -0.74
    ways
    -0.73
    teen
    -0.73
    ures
    -0.71
    lass
    -0.71
    ħ
    -0.71
    POSITIVE LOGITS
    MENT
    0.70
    burg
    0.68
    MENTS
    0.66
     Metatron
    0.63
     guiActiveUnfocused
    0.61
     Ezek
    0.61
     rabbi
    0.61
    mallow
    0.60
    IUM
    0.59
     absor
    0.59
    Act Density 0.033%

    No Known Activations