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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to personal development and behaviors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to self-referential or self-focused concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sea
    -0.75
    QUI
    -0.70
    fif
    -0.69
    STD
    -0.68
    anwhile
    -0.68
    apest
    -0.68
    estone
    -0.67
    netflix
    -0.67
    phase
    -0.66
    eston
    -0.65
    POSITIVE LOGITS
     gratification
    0.68
     attribution
    0.62
     autobiography
    0.61
    ciating
    0.61
    ihilation
    0.61
     Morty
    0.60
     admire
    0.59
     recol
    0.59
     Maced
    0.59
     forgiveness
    0.58
    Act Density 0.063%

    No Known Activations