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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appa
    -0.15
     def
    -0.15
    acker
    -0.14
     Gardner
    -0.14
     establishment
    -0.14
     Justice
    -0.14
    ym
    -0.13
    oui
    -0.13
    566
    -0.13
    tones
    -0.13
    POSITIVE LOGITS
    æŀľ
    0.15
    ovice
    0.15
    edar
    0.15
    fruit
    0.15
    uits
    0.14
    ikit
    0.14
    ogi
    0.14
    ograd
    0.13
    oplayer
    0.13
     republiky
    0.13
    Act Density 0.002%

    No Known Activations