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

    Neuronpedia

    INDEX
    Explanations

    texts in a different language that contain specific characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in punctuation or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.78
    rencies
    -0.74
    ovie
    -0.72
    ieties
    -0.68
    oths
    -0.65
     enrol
    -0.64
    ³³³³
    -0.63
    ³³
    -0.62
     Sapphire
    -0.60
    eworld
    -0.59
    POSITIVE LOGITS
    enance
    0.98
    lings
    0.84
    imates
    0.80
     Leilan
    0.78
    DEN
    0.76
    glers
    0.75
    ten
    0.70
    lations
    0.68
    Esc
    0.67
    rito
    0.67
    Act Density 0.060%

    No Known Activations