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

    Neuronpedia

    INDEX
    Explanations

    locations or places containing particular elements or conditions

    oai_token-act-pair · gpt-3.5-turbo

    words related to expertise or specialized knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.78
     ANGEL
    -0.76
    ADRA
    -0.75
     Incarnation
    -0.72
    Lago
    -0.70
    earchers
    -0.69
    CAP
    -0.68
     Leilan
    -0.68
     Mutant
    -0.67
    boats
    -0.67
    POSITIVE LOGITS
    inent
    1.47
    onso
    1.08
    urbed
    1.06
    urb
    0.94
    ipes
    0.94
    ritional
    0.91
    rient
    0.90
    ures
    0.88
    asters
    0.88
    rey
    0.87
    Act Density 0.023%

    No Known Activations