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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of issues or problem resolutions

    oai_token-act-pair · gpt-3.5-turbo

    references to various issues within a publication or series of publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bones
    -0.82
    wig
    -0.75
    asty
    -0.70
    RAL
    -0.69
    rous
    -0.66
    borg
    -0.66
    carbon
    -0.66
    urses
    -0.66
    glers
    -0.66
    onz
    -0.65
    POSITIVE LOGITS
     tracker
    0.96
    naires
    0.85
     plag
    0.82
     resolved
    0.80
     arises
    0.75
    naire
    0.74
     arose
    0.73
     arise
    0.70
     flared
    0.69
     raised
    0.68
    Act Density 0.067%

    No Known Activations