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

    Neuronpedia

    INDEX
    Explanations

    expressions related to logical structures or code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spiral
    -0.16
     Briggs
    -0.15
    ierce
    -0.15
    Terminal
    -0.14
    ÃŁ
    -0.14
    _union
    -0.14
    /tiny
    -0.14
     Socorro
    -0.14
     Geometry
    -0.13
     ì§ĢëıĦ
    -0.13
    POSITIVE LOGITS
    enza
    0.15
    wan
    0.15
    illis
    0.15
    oux
    0.15
    lep
    0.14
    ripper
    0.14
     wb
    0.14
    leh
    0.14
    LES
    0.14
    Cop
    0.14
    Act Density 0.001%

    No Known Activations