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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "Out" prominently featured

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presume
    -0.65
     gland
    -0.63
    bucks
    -0.60
    rons
    -0.58
    ãĤ·ãĥ£
    -0.58
    loading
    -0.58
    gr
    -0.57
    clock
    -0.57
    CVE
    -0.56
     latitude
    -0.56
    POSITIVE LOGITS
     Out
    3.37
    Out
    2.42
     OUT
    2.08
    out
    1.75
    OUT
    1.71
     Outs
    1.65
    outs
    1.38
     out
    1.37
     Outside
    1.35
     Off
    1.32
    Act Density 0.012%

    No Known Activations