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

    Neuronpedia

    INDEX
    Explanations

    links to full articles, stories, or details associated with various topics

    oai_token-act-pair · gpt-3.5-turbo

    references to complete transcripts or full content summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.77
    ovan
    -0.76
    Downloadha
    -0.71
     whis
    -0.69
    DERR
    -0.68
    uffle
    -0.68
    apons
    -0.67
     Michaels
    -0.66
    pton
    -0.66
    idated
    -0.65
    POSITIVE LOGITS
    erton
    1.14
    screen
    1.04
    ness
    0.79
    bright
    0.77
    text
    0.75
    dress
    0.74
    ening
    0.74
     fled
    0.74
    heartedly
    0.73
     frontal
    0.72
    Act Density 0.026%

    No Known Activations