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

    Neuronpedia

    INDEX
    Explanations

    conditional statements starting with 'If'

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ictionary
    -0.71
    ategories
    -0.67
    orah
    -0.67
    inian
    -0.67
    chant
    -0.66
    Eye
    -0.66
    inosaur
    -0.66
     Originally
    -0.64
    washer
    -0.64
    eware
    -0.63
    POSITIVE LOGITS
     successful
    1.12
     elected
    0.99
     unsuccessful
    0.95
     ratified
    0.80
     unchecked
    0.78
     necessary
    0.78
    successful
    0.76
     reinstated
    0.76
     convicted
    0.75
     confirmed
    0.74
    Act Density 0.135%

    No Known Activations