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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies or evidence-based findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __*/
    -0.56
    SequentialGroup
    -0.53
     gì
    -0.45
    期
    -0.44
    downcase
    -0.40
     createState
    -0.39
    TAWA
    -0.39
    或者
    -0.39
    Autre
    -0.39
    ArgsConstructor
    -0.38
    POSITIVE LOGITS
     including
    2.31
    including
    1.96
     Including
    1.91
    Including
    1.88
     waaronder
    1.81
     incluindo
    1.74
     INCLUDING
    1.68
     incluyendo
    1.63
     darunter
    1.59
     включая
    1.54
    Act Density 0.736%

    No Known Activations