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

    Neuronpedia

    INDEX
    Explanations

    terminology related to progress and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achable
    -0.16
    rig
    -0.16
    esty
    -0.15
    CRET
    -0.15
    owe
    -0.14
    sdale
    -0.14
     Heck
    -0.14
    iska
    -0.14
    ensburg
    -0.14
    olves
    -0.14
    POSITIVE LOGITS
    rypto
    0.15
     Îijν
    0.15
    ocs
    0.14
    ogg
    0.14
    ardi
    0.14
     tribal
    0.14
     Wag
    0.14
     Spell
    0.14
    ès
    0.14
     Anthrop
    0.13
    Act Density 0.009%

    No Known Activations