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

    Neuronpedia

    INDEX
    Explanations

    words related to navigation or guiding through different contexts or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "navigate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onement
    -0.82
    etime
    -0.77
    endi
    -0.74
    riter
    -0.69
    die
    -0.68
    uster
    -0.66
    ¢
    -0.66
    asts
    -0.65
    iaries
    -0.65
    inite
    -0.65
    POSITIVE LOGITS
     navig
    1.06
     navigating
    1.05
     navigate
    1.02
     Navigation
    0.92
     navigation
    0.88
    TAIN
    0.84
     uphill
    0.78
     paths
    0.78
     Mane
    0.76
     travers
    0.74
    Act Density 0.021%

    No Known Activations