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

    Neuronpedia

    INDEX
    Explanations

    phrases related to applause

    oai_token-act-pair · gpt-3.5-turbo

    the word "bo" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.80
    ãĥ´ãĤ¡
    -0.78
    âĶģ
    -0.77
     Sons
    -0.73
    ãĤ®
    -0.71
    UTION
    -0.70
    ãĥ¤
    -0.70
    UAL
    -0.69
     totality
    -0.68
    HCR
    -0.68
    POSITIVE LOGITS
    gey
    1.14
    quet
    0.97
    oby
    0.94
    ogie
    0.93
    oms
    0.91
    atform
    0.89
    jo
    0.88
     bo
    0.88
    ppy
    0.88
    onga
    0.87
    Act Density 0.010%

    No Known Activations