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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confirming or asserting something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to affirmation and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    devices
    -0.78
    OTOS
    -0.76
    DragonMagazine
    -0.76
    NetMessage
    -0.75
     Horses
    -0.73
    sites
    -0.73
    Ox
    -0.71
    pmwiki
    -0.69
    fare
    -0.69
    FIX
    -0.68
    POSITIVE LOGITS
     affirm
    1.29
    irming
    1.25
    irmed
    1.11
    irmation
    1.11
     affirmation
    1.10
    atively
    1.03
    irm
    0.97
     unequivocally
    0.89
    irms
    0.87
    uctor
    0.81
    Act Density 0.013%

    No Known Activations