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

    Neuronpedia

    INDEX
    Explanations

    phrases describing personal attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    conjugations of the verb "to be," particularly in relation to people's characteristics or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.80
    lag
    -0.74
    icipated
    -0.73
    osate
    -0.72
    uld
    -0.72
    sequent
    -0.70
    ocations
    -0.69
    isance
    -0.69
     Login
    -0.69
     Anniversary
    -0.68
    POSITIVE LOGITS
     fearless
    1.31
     charismatic
    1.25
     witty
    1.15
     talented
    1.15
     intelligent
    1.14
     brilliant
    1.13
     versatile
    1.13
     ruthless
    1.12
     smarter
    1.10
     adept
    1.10
    Act Density 0.255%

    No Known Activations