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

    Neuronpedia

    INDEX
    Explanations

    certain words containing the letters 'Sw' and a numerical value following it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "Sw" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uate
    -0.68
    ============
    -0.68
     Mayhem
    -0.63
    ional
    -0.61
    âĸ¬âĸ¬
    -0.61
    ously
    -0.61
     preferential
    -0.61
     partial
    -0.61
     flares
    -0.60
    çķ
    -0.59
    POSITIVE LOGITS
    imming
    1.31
    indle
    1.26
    itched
    1.20
    immer
    1.17
    ollen
    1.15
    artz
    1.13
    ifty
    1.11
    addle
    1.11
    itches
    1.10
    erve
    1.09
    Act Density 0.029%

    No Known Activations