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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "called" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edia
    -0.84
    olitics
    -0.75
    bilt
    -0.71
    inth
    -0.66
    Leaks
    -0.65
    feat
    -0.63
    isode
    -0.63
    SPONSORED
    -0.62
    isman
    -0.62
    _-
    -0.61
    POSITIVE LOGITS
    @#&
    0.68
     '
    0.66
     forth
    0.65
     upon
    0.62
     `
    0.61
    phas
    0.61
     attention
    0.60
     "
    0.60
     ''
    0.59
     disorderly
    0.59
    Act Density 0.063%

    No Known Activations