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

    Neuronpedia

    INDEX
    Explanations

    words related to explosive devices

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the syllable "bo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.85
    Interstitial
    -0.78
    âĶģ
    -0.77
    âķIJ
    -0.76
    UTION
    -0.76
     totality
    -0.70
    ãĤ»
    -0.70
    ãĥ´ãĤ¡
    -0.69
     Sons
    -0.68
     Nadu
    -0.68
    POSITIVE LOGITS
    gey
    1.13
    ogie
    1.01
    quet
    0.98
    zz
    0.97
    oby
    0.94
    jo
    0.93
    ambo
    0.93
    oths
    0.93
    onga
    0.92
    oche
    0.91
    Act Density 0.009%

    No Known Activations