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

    Neuronpedia

    INDEX
    Explanations

    instances of comparative or quantifying language that indicate selection, choice, and layering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atif
    -0.17
     ones
    -0.17
     person
    -0.17
     reasons
    -0.15
    utut
    -0.15
    ffen
    -0.14
     someone
    -0.14
    PushMatrix
    -0.14
     inquiries
    -0.14
     holders
    -0.14
    POSITIVE LOGITS
     participants
    0.39
     Participants
    0.36
     participant
    0.36
    participants
    0.33
    Participants
    0.33
     Participant
    0.32
     participating
    0.32
    Participant
    0.29
    participant
    0.29
     PARTIC
    0.27
    Act Density 0.026%

    No Known Activations