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

    Neuronpedia

    INDEX
    Explanations

    terms related to tightness or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoot
    -0.15
     Laz
    -0.14
    iverz
    -0.14
    pekt
    -0.14
     muj
    -0.14
     addCriterion
    -0.14
    hoe
    -0.14
     пал
    -0.14
    ello
    -0.13
    cod
    -0.13
    POSITIVE LOGITS
    ening
    0.27
    ness
    0.25
    est
    0.23
    ened
    0.22
     knit
    0.21
    /loose
    0.21
     tight
    0.21
    tight
    0.21
    ens
    0.20
    emann
    0.20
    Act Density 0.012%

    No Known Activations