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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate dialogue or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uisse
    -0.15
     blink
    -0.14
    ighted
    -0.14
    rado
    -0.14
    _DEFINE
    -0.14
    _HINT
    -0.14
     Said
    -0.13
     бли
    -0.13
    Suddenly
    -0.13
    egt
    -0.13
    POSITIVE LOGITS
     shouldn
    0.16
     Gods
    0.15
    849
    0.15
    tion
    0.15
     Ang
    0.15
     _
    0.14
    -of
    0.14
     bile
    0.14
     bitte
    0.14
    aybe
    0.14
    Act Density 0.236%

    No Known Activations