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

    Neuronpedia

    INDEX
    Explanations

    special characters occurring in a repeating pattern

    oai_token-act-pair · gpt-3.5-turbo

    non-alphanumeric characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.70
    hang
    -0.61
     dissu
    -0.58
    roman
    -0.58
    utical
    -0.58
    atis
    -0.58
    iannopoulos
    -0.57
    umers
    -0.57
    alions
    -0.56
    udeau
    -0.55
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.96
    ³³³³³³³³
    0.89
    ³³³
    0.83
    ³³³³
    0.83
    ³³
    0.76
    Ear
    0.72
    ↵Âł
    0.70
    yrics
    0.68
    ente
    0.68
    Contents
    0.67
    Act Density 0.183%

    No Known Activations