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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluation or judgment, especially focusing on qualities like certainty, confidence, importance, and intensity

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Avenger
    -0.80
     Summoner
    -0.76
     unsigned
    -0.71
     Valkyrie
    -0.70
     Sleeping
    -0.70
     Confederacy
    -0.68
    odd
    -0.66
     Avengers
    -0.66
     Cavs
    -0.65
     nests
    -0.64
    POSITIVE LOGITS
    abl
    0.89
     guiActiveUn
    0.83
     srfAttach
    0.80
    abwe
    0.79
    bole
    0.77
    say
    0.77
     abandon
    0.77
    fare
    0.76
    ateurs
    0.75
    aces
    0.75
    Act Density 10.092%

    No Known Activations