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

    Neuronpedia

    INDEX
    Explanations

    phrases related to highlighting or emphasizing certain points

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or anticipation about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.71
    umbn
    -0.70
    elfth
    -0.69
    andise
    -0.64
     Instr
    -0.63
    gerald
    -0.62
    ij士
    -0.60
    appropriately
    -0.57
    ãĥĹ
    -0.56
    orough
    -0.55
    POSITIVE LOGITS
    )?
    0.95
    ¶
    0.90
     ;)
    0.83
     ;
    0.79
     :)
    0.78
    !!!!
    0.77
     !!
    0.77
     :-)
    0.76
    ?),
    0.75
     ):
    0.75
    Act Density 0.930%

    No Known Activations