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

    Neuronpedia

    INDEX
    Explanations

    words related to carrying or transporting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ha" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.81
    geist
    -0.68
     multiplier
    -0.67
    sburgh
    -0.65
    naire
    -0.62
    imates
    -0.61
    oulos
    -0.60
    Leaks
    -0.60
     bulletin
    -0.59
    icipated
    -0.58
    POSITIVE LOGITS
    pless
    1.14
    ugh
    1.13
    ilst
    1.12
    ilty
    1.00
    ird
    0.98
    ptic
    0.98
    ired
    0.97
    ilt
    0.97
    uling
    0.96
    pt
    0.95
    Act Density 0.016%

    No Known Activations