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

    Neuronpedia

    INDEX
    Explanations

    terms related to turbochargers and engines

    oai_token-act-pair · gpt-3.5-turbo

    references to turbo mechanics or turbocharged systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.85
     Debor
    -0.81
     Flavoring
    -0.78
     Correspond
    -0.74
    */(
    -0.73
    aniel
    -0.73
    olson
    -0.72
     Caption
    -0.71
    guyen
    -0.71
    代
    -0.70
    POSITIVE LOGITS
    charged
    1.41
    charging
    1.30
    charg
    1.24
    charges
    1.00
    charge
    0.95
    Gra
    0.89
    blast
    0.83
     absor
    0.82
    itialized
    0.80
     turbo
    0.78
    Act Density 0.017%

    No Known Activations