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

    Neuronpedia

    INDEX
    Explanations

    percentages or frequency-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opi
    -0.16
     Sanford
    -0.15
    lean
    -0.15
    pio
    -0.15
    ogo
    -0.14
     sterile
    -0.14
    546
    -0.14
    ngr
    -0.14
    inv
    -0.14
    radient
    -0.14
    POSITIVE LOGITS
    heimer
    0.17
    ayet
    0.16
    azer
    0.15
     azal
    0.15
    worth
    0.15
    awl
    0.14
    ace
    0.14
    á»ĩn
    0.14
    vard
    0.14
    á»ĩu
    0.14
    Act Density 0.001%

    No Known Activations