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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    articles preceding nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffs
    -0.81
    casters
    -0.78
    ATURES
    -0.77
    fn
    -0.71
    /-
    -0.71
    âĿ
    -0.70
    marks
    -0.68
    nil
    -0.67
    stars
    -0.67
    ontent
    -0.67
    POSITIVE LOGITS
     nutshell
    1.18
     vein
    1.04
     manner
    1.03
     vain
    1.00
     guise
    0.97
     hurry
    0.95
     densely
    0.92
     crowded
    0.91
     dense
    0.90
     timely
    0.89
    Act Density 0.171%

    No Known Activations