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

    Neuronpedia

    INDEX
    Explanations

    dates and time expressions like "hour", "days after", "30 and 6:30 am", "minutes into"

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vre
    -0.75
    ãĤ´ãĥ³
    -0.71
    urally
    -0.70
    ongevity
    -0.69
    opia
    -0.63
    Really
    -0.63
    agine
    -0.62
    alo
    -0.62
    ãĤ¦ãĤ¹
    -0.61
    far
    -0.60
    POSITIVE LOGITS
     however
    0.84
     CTR
    0.77
     rumors
    0.77
     someone
    0.70
    FTWARE
    0.70
     appellant
    0.68
     assailants
    0.68
    someone
    0.68
     she
    0.68
     TMZ
    0.67
    Act Density 0.220%

    No Known Activations