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

    Neuronpedia

    INDEX
    Explanations

    negatives or the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Various
    -0.22
     Numerous
    -0.18
    Various
    -0.17
     various
    -0.16
    ucci
    -0.15
    patrick
    -0.15
    empo
    -0.15
     Things
    -0.15
    ÑĢо
    -0.15
     whatever
    -0.14
    POSITIVE LOGITS
    -one
    0.34
    thin
    0.34
    xious
    0.32
     longer
    0.29
    isy
    0.28
    one
    0.26
    things
    0.26
     discern
    0.26
     mention
    0.25
    BODY
    0.24
    Act Density 0.110%

    No Known Activations