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

    Neuronpedia

    INDEX
    Explanations

    capitalized words starting with 'for'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "For" along with its various forms and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mare
    -0.58
    å£
    -0.56
    aminer
    -0.55
    inese
    -0.55
    801
    -0.55
    orically
    -0.54
     Parsons
    -0.53
     jaws
    -0.53
     BELOW
    -0.52
     regards
    -0.51
    POSITIVE LOGITS
    bidden
    1.50
    gotten
    1.45
    gery
    1.20
    ked
    1.15
    geries
    1.14
    cible
    1.08
    gettable
    1.06
    got
    1.04
     example
    1.04
     instance
    1.02
    Act Density 0.064%

    No Known Activations