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

    Neuronpedia

    INDEX
    Explanations

    names with a specific pattern: starting with "Schwe" or "Schultz" followed by a digit from 1 to 10

    oai_token-act-pair · gpt-3.5-turbo

    names or variations of the name "Schwe" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icative
    -0.74
     Grateful
    -0.70
    ELY
    -0.66
    GBT
    -0.66
    vernment
    -0.66
    ARY
    -0.65
     Xer
    -0.61
     Gleaming
    -0.61
    DragonMagazine
    -0.59
    icably
    -0.59
    POSITIVE LOGITS
    midt
    1.08
    uler
    1.02
    thal
    0.94
    izophren
    0.87
    olars
    0.87
    arma
    0.86
    olar
    0.84
    acters
    0.83
    ultz
    0.81
    okes
    0.81
    Act Density 0.026%

    No Known Activations