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

    Neuronpedia

    INDEX
    Explanations

    technical terms and codes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to global or widespread concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flavorful
    -0.55
     behavi
    -0.55
     convol
    -0.53
     suspic
    -0.53
     GOODMAN
    -0.51
     viewing
    -0.51
     retaining
    -0.51
     scrut
    -0.50
     rooting
    -0.50
    staking
    -0.48
    POSITIVE LOGITS
    ensis
    0.80
    Topic
    0.68
    wordpress
    0.66
    âĢİ
    0.65
    yahoo
    0.63
    ilet
    0.61
    çļĦ
    0.61
    airo
    0.60
    dq
    0.58
    []
    0.58
    Act Density 0.584%

    No Known Activations