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

    Neuronpedia

    INDEX
    Explanations

    mentions of additional or bonus items or features

    oai_token-act-pair · gpt-3.5-turbo

    instances of additional information or details in lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Really
    -0.86
    ãĤ¦ãĤ¹
    -0.79
    Sure
    -0.71
    cffffcc
    -0.71
    reason
    -0.70
    Certainly
    -0.70
    é¾įå¥ij士
    -0.69
    Yet
    -0.69
     Really
    -0.67
    really
    -0.67
    POSITIVE LOGITS
     we
    0.87
     there
    0.73
     including
    0.72
     entrants
    0.70
     researchers
    0.69
     representatives
    0.69
     participants
    0.68
     astronomers
    0.65
     archaeologists
    0.64
     they
    0.63
    Act Density 0.345%

    No Known Activations