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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to explaining or describing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to definitions and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     maneu
    -0.69
     thrive
    -0.67
    archive
    -0.62
    bj
    -0.62
    win
    -0.61
    qus
    -0.61
    Whe
    -0.60
     ensued
    -0.59
    wr
    -0.59
    ath
    -0.59
    POSITIVE LOGITS
     Franch
    0.73
     guiName
    0.69
    gdala
    0.69
     derog
    0.68
     figur
    0.67
     joking
    0.66
    isSpecialOrderable
    0.65
     lightly
    0.64
    =#
    0.63
     metaphor
    0.61
    Act Density 0.429%

    No Known Activations