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

    Neuronpedia

    INDEX
    Explanations

    expressions related to decision-making and evaluations of circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    disposition or reasoning before a clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.28
     myſelf
    -1.23
     Efq
    -1.23
     Jefus
    -1.20
     raiſ
    -1.17
    ſelf
    -1.16
     Majefty
    -1.13
     Houſe
    -1.13
    ſelves
    -1.12
     Forumite
    -1.11
    POSITIVE LOGITS
    ,
    0.58
     &
    0.55
     that
    0.51
    .
    0.49
     in
    0.49
    :
    0.45
     even
    0.44
    j
    0.44
     for
    0.43
     if
    0.43
    Act Density 0.207%

    No Known Activations