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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating certainty or assessment of condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aste
    -0.62
    cot
    -0.62
     Sierra
    -0.62
    regate
    -0.61
    scl
    -0.59
    ries
    -0.58
    enment
    -0.57
    ussions
    -0.56
    rowth
    -0.56
    ourses
    -0.56
    POSITIVE LOGITS
    hett
    0.72
    ðŁ
    0.67
    ãĥķãĤ©
    0.66
     understatement
    0.64
     cousins
    0.63
    aware
    0.62
    INO
    0.61
    GoldMagikarp
    0.60
     obser
    0.59
     Beir
    0.58
    Act Density 0.267%

    No Known Activations