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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "within" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate internal contexts or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enez
    -0.74
    ãĥ£
    -0.69
    rod
    -0.68
    tec
    -0.68
    ãĤ·ãĥ£
    -0.67
    ple
    -0.67
    ãĥĹ
    -0.64
    é¾į
    -0.64
    rw
    -0.64
     goodbye
    -0.63
    POSITIVE LOGITS
    imore
    0.93
    isine
    0.79
    animate
    0.77
     bounds
    0.75
     parentheses
    0.73
    izabeth
    0.72
    ciating
    0.71
     orbit
    0.70
    ¥ŀ
    0.69
    isode
    0.68
    Act Density 0.026%

    No Known Activations