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

    Neuronpedia

    INDEX
    Explanations

    programmatic elements related to questions or interaction prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ABCDEFGHIJKLMNOP
    -0.07
    ãĥĥãĤ¯ãĤ¹
    -0.06
     hấp
    -0.06
    omen
    -0.06
    ARN
    -0.06
    LD
    -0.06
     tales
    -0.06
     ÙĤاب
    -0.06
    865
    -0.06
    #ad
    -0.06
    POSITIVE LOGITS
     reply
    0.07
    Reply
    0.07
    reply
    0.07
    åĮ
    0.07
    attachment
    0.07
    isas
    0.07
    ipy
    0.07
    hil
    0.07
    ÅĻad
    0.06
     Revel
    0.06
    Act Density 0.011%

    No Known Activations