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

    Neuronpedia

    INDEX
    Explanations

    names or references related to a specific character or series, potentially from literature or entertainment sources

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.83
    rador
    -0.81
    spring
    -0.77
     Carbuncle
    -0.75
    achusetts
    -0.74
    ernaut
    -0.72
    iosity
    -0.71
    enance
    -0.70
    lishes
    -0.68
    eatures
    -0.68
    POSITIVE LOGITS
    gas
    0.99
    IRO
    0.86
    hyde
    0.83
    jad
    0.83
    vich
    0.82
    cia
    0.81
    agle
    0.78
    gger
    0.76
    zie
    0.76
    geon
    0.75
    Act Density 0.140%

    No Known Activations