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

    Neuronpedia

    INDEX
    Explanations

    expressions related to conflict, struggle, or tension

    oai_token-act-pair · gpt-3.5-turbo

    special characters and punctuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĵ
    -0.71
    emic
    -0.65
    ãĤ¶
    -0.65
    cient
    -0.63
     compiled
    -0.63
    ichi
    -0.63
    ãĥ«
    -0.62
    jit
    -0.61
    mos
    -0.61
    stein
    -0.61
    POSITIVE LOGITS
     Lastly
    0.84
     Ibid
    0.84
    âĵĺ
    0.83
    \<
    0.75
     Fn
    0.73
     Flavoring
    0.72
    endif
    0.71
    catentry
    0.69
     Picks
    0.66
    Conclusion
    0.66
    Act Density 0.372%

    No Known Activations