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

    Neuronpedia

    INDEX
    Explanations

    words related to strength or success

    oai_token-act-pair · gpt-3.5-turbo

    the word "strong" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sloan
    -0.78
     Canaver
    -0.75
    Hop
    -0.75
     Correction
    -0.67
     externalToEVAOnly
    -0.66
    hops
    -0.66
    oleon
    -0.65
     Journals
    -0.65
    adr
    -0.64
    arthed
    -0.64
    POSITIVE LOGITS
     enough
    1.11
    enough
    1.04
    nesses
    0.87
    ener
    0.83
     contender
    0.81
    sword
    0.80
     Enough
    0.79
     winds
    0.78
     deterrent
    0.76
     emphasis
    0.75
    Act Density 0.037%

    No Known Activations