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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives intensifying emotions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enthusiasm or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Attend
    -0.70
    DragonMagazine
    -0.65
     Settlement
    -0.64
    à©
    -0.63
     Proceedings
    -0.63
     cessation
    -0.63
    uments
    -0.62
    igate
    -0.62
     Vend
    -0.62
     Canaver
    -0.62
    POSITIVE LOGITS
    imposed
    1.20
    nova
    1.04
    charged
    1.04
    charges
    0.93
    cedes
    0.91
    powers
    0.87
    ced
    0.83
    cil
    0.83
     awesome
    0.81
    visor
    0.78
    Act Density 0.031%

    No Known Activations