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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating personal possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.58
     Awakens
    -0.52
    ESE
    -0.50
    iates
    -0.50
     Moines
    -0.50
    uese
    -0.50
    aturdays
    -0.49
     Benefits
    -0.49
     Highlights
    -0.49
    ilst
    -0.49
    POSITIVE LOGITS
    nt
    0.88
     supposed
    0.78
     unlikely
    0.73
     not
    0.72
     definitely
    0.72
     hereby
    0.70
    rael
    0.68
     gonna
    0.68
     bound
    0.67
     NOT
    0.67
    Act Density 0.746%

    No Known Activations