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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a general overview or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "all" and variations of "in" expressing inclusivity or collective contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.91
     [|
    -0.70
    actively
    -0.69
    ainer
    -0.66
    antry
    -0.63
    vp
    -0.63
    igm
    -0.63
    uca
    -0.63
    oise
    -0.62
    agram
    -0.62
    POSITIVE LOGITS
     notwithstanding
    0.77
     aside
    0.76
     except
    0.73
     assumes
    0.73
     proceeds
    0.67
     culmin
    0.65
     haste
    0.65
     combined
    0.65
     meshes
    0.64
    endif
    0.64
    Act Density 0.113%

    No Known Activations