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

    Neuronpedia

    INDEX
    Explanations

    sentences that introduce or emphasize a statement

    oai_token-act-pair · gpt-3.5-turbo

    statements that assert or define a concept or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bies
    -0.79
    luaj
    -0.73
    mons
    -0.64
     pedest
    -0.63
    actory
    -0.62
    itches
    -0.61
    cies
    -0.61
     mull
    -0.60
     maiden
    -0.59
     throats
    -0.58
    POSITIVE LOGITS
    rael
    0.87
    claimer
    0.80
    nt
    0.80
    olation
    0.75
     definitely
    0.73
     Hardcore
    0.72
    hemy
    0.71
    ĥ
    0.71
     Mahjong
    0.69
    ĻĤ
    0.68
    Act Density 0.122%

    No Known Activations