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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions unraveling or deciphering something

    oai_token-act-pair · gpt-3.5-turbo

    words related to revealing or solving complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eworld
    -0.61
    FORE
    -0.60
    --+
    -0.60
    gged
    -0.59
     reserved
    -0.58
     Fo
    -0.58
    eral
    -0.57
     Zam
    -0.56
    âĢij
    -0.56
    cium
    -0.55
    POSITIVE LOGITS
    edIn
    1.03
     unravel
    0.96
    ing
    0.92
    ĸļ
    0.80
    lement
    0.79
    ed
    0.78
    eering
    0.76
    schild
    0.75
    icter
    0.75
    stakes
    0.74
    Act Density 0.015%

    No Known Activations