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

    Neuronpedia

    INDEX
    Explanations

    phrases where the speaker expresses certainty or strong belief towards a statement

    oai_token-act-pair · gpt-3.5-turbo

    statements of agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    works
    -0.57
    NF
    -0.55
    pace
    -0.54
     RIS
    -0.54
     curve
    -0.54
     collision
    -0.53
     pitches
    -0.53
     resemblance
    -0.52
    dust
    -0.52
     Gaw
    -0.52
    POSITIVE LOGITS
    bered
    1.19
    oths
    1.17
    apy
    1.08
    othes
    1.00
    oner
    1.00
    othe
    0.96
    iled
    0.92
    zin
    0.86
    arer
    0.84
    iling
    0.84
    Act Density 0.069%

    No Known Activations