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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to research and analysis methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umph
    -0.08
    deps
    -0.07
    dont
    -0.07
     Might
    -0.07
    codegen
    -0.07
    ottom
    -0.06
     spol
    -0.06
     Had
    -0.06
     TCHAR
    -0.06
     Went
    -0.06
    POSITIVE LOGITS
     was
    0.16
     were
    0.14
    was
    0.12
     бÑĭла
    0.10
     zosta
    0.10
     werd
    0.10
    were
    0.10
     are
    0.10
     бÑĭл
    0.10
     fueron
    0.09
    Act Density 0.148%

    No Known Activations