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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions or directives

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal actions and directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nai
    -0.67
    rawdownloadcloneembedreportprint
    -0.60
     folklore
    -0.60
     somew
    -0.60
     Surviv
    -0.58
     Coliseum
    -0.58
    ival
    -0.58
    BALL
    -0.58
     Loft
    -0.58
    ebus
    -0.57
    POSITIVE LOGITS
    motion
    1.10
    ão
    0.85
    repeat
    0.80
    isance
    0.72
    assment
    0.72
    Motion
    0.71
    encia
    0.71
    fen
    0.66
    start
    0.66
    amaz
    0.66
    Act Density 0.085%

    No Known Activations