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

    Neuronpedia

    INDEX
    Explanations

    quotes among the text

    oai_token-act-pair · gpt-3.5-turbo

    quotations and dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bragging
    -0.75
     girlfriends
    -0.71
     nig
    -0.69
     whim
    -0.68
     Saiyan
    -0.66
    tumblr
    -0.65
     feud
    -0.64
     vacation
    -0.64
     pray
    -0.64
     pageant
    -0.64
    POSITIVE LOGITS
    olin
    0.82
    cosystem
    0.80
    itsch
    0.78
    Therefore
    0.78
    Finding
    0.77
    Understanding
    0.76
    atform
    0.75
    ulty
    0.75
    Prof
    0.75
    resso
    0.75
    Act Density 0.316%

    No Known Activations