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

    Neuronpedia

    INDEX
    Explanations

    numerical data, particularly related to statistics and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olik
    -0.16
     Kendrick
    -0.15
    FindBy
    -0.15
    302
    -0.14
    763
    -0.14
     mur
    -0.14
    okus
    -0.14
    mith
    -0.14
     habit
    -0.14
     Haley
    -0.14
    POSITIVE LOGITS
    180
    0.42
    280
    0.40
    170
    0.40
    480
    0.39
    160
    0.39
    130
    0.38
    240
    0.38
    360
    0.38
    190
    0.37
    120
    0.37
    Act Density 0.190%

    No Known Activations