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

    Neuronpedia

    INDEX
    Explanations

    time expressions written in numerical format

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     parach
    -0.65
     paranormal
    -0.60
     mixer
    -0.59
     interf
    -0.58
     omn
    -0.58
     iceberg
    -0.58
     insurrection
    -0.57
     imperson
    -0.55
     antidote
    -0.55
     investigative
    -0.54
    POSITIVE LOGITS
    06
    1.51
    08
    1.51
    05
    1.50
    09
    1.47
    07
    1.43
    00
    1.42
    04
    1.42
    02
    1.41
    03
    1.38
    95
    1.37
    Act Density 0.090%

    No Known Activations