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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spreading information or messages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to spreading information and positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģĸ
    -0.71
     reckoning
    -0.70
    ĻĤ
    -0.67
    tein
    -0.66
    trak
    -0.65
    ||
    -0.63
    ¥µ
    -0.59
     converter
    -0.59
     poised
    -0.58
    âĢķ
    -0.58
    POSITIVE LOGITS
    sheets
    0.82
    izont
    0.79
    weekly
    0.78
    igham
    0.75
    pread
    0.75
     spreads
    0.71
     thinly
    0.71
     pamph
    0.70
     horizontally
    0.70
    eret
    0.69
    Act Density 0.127%

    No Known Activations