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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references such as statistics or citation formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hack
    -0.16
    ose
    -0.14
    cube
    -0.14
     Vz
    -0.14
     Hack
    -0.14
     erót
    -0.14
    afi
    -0.13
    uger
    -0.13
     Arrest
    -0.13
    alus
    -0.13
    POSITIVE LOGITS
     cam
    0.16
    DAC
    0.16
    enic
    0.16
    hir
    0.15
    ãĥ³ãĥ
    0.15
    lexer
    0.14
    âĶIJ
    0.14
    lacak
    0.14
     cellForRowAt
    0.14
     prelim
    0.14
    Act Density 0.044%

    No Known Activations