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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing quantity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    repetitive expressions of abundance or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aves
    -0.85
    ares
    -0.84
    ħĭ
    -0.81
    save
    -0.78
    Ts
    -0.78
    adas
    -0.78
    ooters
    -0.78
    endars
    -0.77
    ãĥ¼ãĥ³
    -0.75
    opers
    -0.74
    POSITIVE LOGITS
     overlap
    1.20
     ambiguity
    1.15
     uncertainty
    1.14
     variability
    1.14
     disagreement
    1.12
     confusion
    1.11
     misinformation
    1.10
     evidence
    1.06
     animosity
    1.03
     speculation
    1.01
    Act Density 0.135%

    No Known Activations