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

    Neuronpedia

    INDEX
    Explanations

    phrases related to boundaries or limits

    oai_token-act-pair · gpt-3.5-turbo

    the word "within" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enez
    -0.71
    ãĥ£
    -0.70
    ãĥĵ
    -0.70
    ple
    -0.69
    ãĤ·ãĥ£
    -0.68
    ãĥĹ
    -0.66
    é¾į
    -0.66
    rod
    -0.66
    mil
    -0.65
    tec
    -0.65
    POSITIVE LOGITS
    imore
    0.89
    isine
    0.83
    ¥ŀ
    0.77
    ciating
    0.75
    izabeth
    0.75
    animate
    0.74
    ieth
    0.70
    atform
    0.70
     parentheses
    0.70
    isode
    0.69
    Act Density 0.026%

    No Known Activations