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

    Neuronpedia

    INDEX
    Explanations

    words related to arrows

    oai_token-act-pair · gpt-3.5-turbo

    references to arrows in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.75
    Upload
    -0.73
    inen
    -0.71
    ĨĴ
    -0.68
    eanor
    -0.68
    idency
    -0.66
    Rated
    -0.66
    AUD
    -0.66
    crime
    -0.65
    ĸļ
    -0.65
    POSITIVE LOGITS
     arrow
    1.08
     arrows
    1.00
     shaft
    0.94
    heads
    0.92
    fish
    0.89
     protr
    0.88
    head
    0.87
     prope
    0.84
    eers
    0.81
    balls
    0.81
    Act Density 0.018%

    No Known Activations