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

    Neuronpedia

    INDEX
    Explanations

    phrases related to skepticism or concern

    oai_token-act-pair · gpt-3.5-turbo

    casual expressions of personal opinion or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.70
     plurality
    -0.65
    ¥ŀ
    -0.61
     breadth
    -0.61
     sovere
    -0.59
    ensibly
    -0.58
    ãĥ©ãĥ³
    -0.57
     discont
    -0.56
     juven
    -0.55
    âĢij
    -0.55
    POSITIVE LOGITS
     ;)
    1.88
     :)
    1.84
     haha
    1.68
     :-)
    1.67
     :(
    1.59
     ðŁĻĤ
    1.57
     lol
    1.53
    !!
    1.53
     ðŁĺ
    1.52
    !!!!
    1.52
    Act Density 0.611%

    No Known Activations