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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obstacles and problems in various contexts

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

    preceding "in" and "of"

    np_acts-logits-general · gemini-2.0-flash

    problems, factors, signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.37
    午
    -0.32
     ​
    -0.31
     zugesch
    -0.30
     Bupati
    -0.30
     без
    -0.30
    看似
    -0.30
    Gesam
    -0.30
     ügy
    -0.30
     Ketua
    -0.30
    POSITIVE LOGITS
     resourceCulture
    0.63
    OGND
    0.60
    Tembelea
    0.56
    ergies
    0.55
     ſche
    0.55
     HttpNotFound
    0.54
     ſtate
    0.54
    ᐝ
    0.51
     itſelf
    0.51
    <unused41>
    0.50
    Act Density 0.771%

    No Known Activations