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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positioning or location

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or association with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apest
    -0.80
     ILCS
    -0.69
    ļéĨĴ
    -0.69
    SPONSORED
    -0.65
    Spread
    -0.63
    enegger
    -0.62
    --------------------------------------------------------
    -0.61
    ious
    -0.61
    DERR
    -0.60
     Paste
    -0.60
    POSITIVE LOGITS
    agate
    0.68
     things
    0.67
    agons
    0.65
    itol
    0.63
    isSpecialOrderable
    0.62
     angels
    0.61
    enhagen
    0.61
    effects
    0.60
    idges
    0.60
    dark
    0.59
    Act Density 0.091%

    No Known Activations