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

    Neuronpedia

    INDEX
    Explanations

    names or titles with initials followed by numbers or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates or time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.84
     destro
    -0.81
     territ
    -0.77
     manif
    -0.77
     purs
    -0.75
     mathemat
    -0.75
     exha
    -0.75
     appe
    -0.75
     diseng
    -0.73
     neighb
    -0.73
    POSITIVE LOGITS
    Reviewed
    1.28
    Contribut
    1.24
    Posted
    1.23
    Trivia
    1.22
    Updated
    1.20
    Latest
    1.19
    Join
    1.18
    Details
    1.18
    Written
    1.16
    RAW
    1.16
    Act Density 0.089%

    No Known Activations