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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "True Detective"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "True"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hetti
    -0.78
    ciation
    -0.75
    lectic
    -0.73
    #$#$
    -0.72
    */(
    -0.70
    ELS
    -0.70
    ulating
    -0.69
    ETS
    -0.69
    ulative
    -0.68
    joining
    -0.68
    POSITIVE LOGITS
    True
    0.83
     True
    0.77
    False
    0.77
     Temper
    0.76
    bone
    0.70
    ãĥĻ
    0.70
     Colors
    0.69
     Tone
    0.68
    blooded
    0.67
    fit
    0.67
    Act Density 0.008%

    No Known Activations