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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing positive qualities or advancements

    oai_token-act-pair · gpt-3.5-turbo

    affirmative statements or assertions about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urches
    -0.69
    iates
    -0.65
    umbers
    -0.64
    uum
    -0.63
    eor
    -0.63
    apixel
    -0.61
    iate
    -0.61
    thing
    -0.61
    perate
    -0.60
    ivil
    -0.60
    POSITIVE LOGITS
    ometric
    0.89
     undoubtedly
    0.82
    DN
    0.71
     evidenced
    0.66
     definitely
    0.64
    omorphic
    0.63
     doubtless
    0.61
     indeed
    0.61
     Solitaire
    0.61
    cussion
    0.61
    Act Density 0.116%

    No Known Activations