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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various issues and problems

    oai_token-act-pair · gpt-3.5-turbo

    references to incidents or important events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cedes
    -0.68
    ascript
    -0.65
    _____
    -0.64
    chairs
    -0.63
     lasts
    -0.62
    orum
    -0.62
    ims
    -0.62
    ["
    -0.62
    thening
    -0.61
    æ
    -0.60
    POSITIVE LOGITS
    ymm
    0.72
     perenn
    0.71
     perennial
    0.70
     Glac
    0.62
     Butt
    0.62
    mosp
    0.61
    atable
    0.61
    abwe
    0.60
    apo
    0.60
     obligatory
    0.60
    Act Density 0.170%

    No Known Activations