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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional information or content to be read

    oai_token-act-pair · gpt-3.5-turbo

    ellipsis or truncated content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.78
    ally
    -0.68
    itudes
    -0.67
    Ł
    -0.65
    ãĥ«
    -0.60
    ially
    -0.59
     suspic
    -0.59
    ality
    -0.59
    xtap
    -0.59
    ifully
    -0.58
    POSITIVE LOGITS
     Appears
    0.76
    BUT
    0.71
    wait
    0.71
    ahime
    0.70
     âĢİ
    0.70
     Bake
    0.69
     Author
    0.65
    BACK
    0.63
    Hunt
    0.62
    \<
    0.61
    Act Density 0.060%

    No Known Activations