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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "being" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quan
    -0.17
    unger
    -0.15
     Horse
    -0.15
    horse
    -0.15
    enstein
    -0.14
    ximo
    -0.14
    ldkf
    -0.13
    bersome
    -0.13
    acks
    -0.13
    adients
    -0.13
    POSITIVE LOGITS
    irut
    0.15
    بت
    0.15
    atus
    0.14
     spite
    0.13
     worn
    0.13
    ovenant
    0.13
     Doch
    0.13
    uiltin
    0.13
    Structured
    0.13
    omy
    0.13
    Act Density 0.052%

    No Known Activations