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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speculation or prediction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe potential appearances or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osi
    -0.60
    signed
    -0.59
     Quit
    -0.57
    moon
    -0.54
    tap
    -0.54
     detectives
    -0.54
     Fever
    -0.53
    arms
    -0.53
    vette
    -0.53
     mention
    -0.52
    POSITIVE LOGITS
     unfolding
    0.74
    ãĤ¼ãĤ¦ãĤ¹
    0.74
    falls
    0.72
    urities
    0.71
    nings
    0.71
    ãĤ´
    0.67
    Ô
    0.65
    abouts
    0.65
     GOODMAN
    0.64
     versus
    0.63
    Act Density 0.220%

    No Known Activations