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

    Neuronpedia

    INDEX
    Explanations

    phrases related to barriers or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    references to barriers or obstructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.77
     Gravity
    -0.66
    gate
    -0.66
    stakes
    -0.64
    arrell
    -0.64
    sburgh
    -0.63
    mallow
    -0.63
    Penn
    -0.62
    tip
    -0.62
     Dull
    -0.61
    POSITIVE LOGITS
    ulously
    0.82
    uments
    0.82
    uble
    0.81
    ols
    0.78
     barric
    0.78
    abilia
    0.76
     inval
    0.76
    ilitary
    0.74
    lio
    0.72
    kered
    0.72
    Act Density 0.051%

    No Known Activations