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

    Neuronpedia

    INDEX
    Explanations

    references to physical objects and their location or placement

    oai_token-act-pair · gpt-3.5-turbo

    statements of existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ients
    -0.85
    ions
    -0.70
    isms
    -0.70
    uum
    -0.69
    players
    -0.68
    iets
    -0.67
    vertis
    -0.66
    Enlarge
    -0.66
    IQ
    -0.64
    imeters
    -0.63
    POSITIVE LOGITS
     another
    0.89
     an
    0.75
     a
    0.74
     Lieutenant
    0.62
     something
    0.60
     the
    0.60
     Carmen
    0.59
     Mechdragon
    0.59
     priceless
    0.58
     Rei
    0.57
    Act Density 0.074%

    No Known Activations