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

    Neuronpedia

    INDEX
    Explanations

    declarative statements indicating certainty or strong belief

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing certainty and lack of doubt regarding a statement or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lite
    -0.79
     Chains
    -0.78
    ÃĥÃĤ
    -0.75
     pione
    -0.74
     practition
    -0.73
    eah
    -0.72
    ð
    -0.70
    bor
    -0.68
    isSpecial
    -0.68
    umbn
    -0.67
    POSITIVE LOGITS
     whatsoever
    1.11
     mark
    0.75
    AAF
    0.70
    orial
    0.66
     denying
    0.65
    iasis
    0.65
    ANCE
    0.65
     adren
    0.65
     distortion
    0.63
     indicating
    0.63
    Act Density 0.048%

    No Known Activations