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

    Neuronpedia

    INDEX
    Explanations

    occurrences of tilde characters, indicating some form of special notation or emphasis in data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.17
    /or
    -0.17
    ials
    -0.16
    pai
    -0.15
    æľ
    -0.15
    sing
    -0.15
    undy
    -0.14
    wick
    -0.14
    iny
    -0.14
    lee
    -0.14
    POSITIVE LOGITS
    yer
    0.18
     vast
    0.17
    e
    0.15
    artin
    0.15
    ï¸ı
    0.15
    ingly
    0.15
    ively
    0.14
    eb
    0.14
    lassen
    0.14
    eriod
    0.14
    Act Density 0.036%

    No Known Activations