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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing potentially controversial or sensational statements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation that signifies significant statements or transitions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.77
    ixt
    -0.75
     befriend
    -0.74
    ilded
    -0.72
    icultural
    -0.70
    utor
    -0.69
    »Ĵ
    -0.69
    ¬¼
    -0.68
     groove
    -0.68
     encount
    -0.68
    POSITIVE LOGITS
     Others
    1.10
     However
    1.06
     Apparently
    1.02
    Sounds
    1.01
     implying
    1.01
     Presumably
    0.99
     Sounds
    0.99
     Meaning
    0.98
     Personally
    0.98
     Hmm
    0.94
    Act Density 0.902%

    No Known Activations