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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otas
    -0.15
    tracted
    -0.15
    zf
    -0.14
    akens
    -0.14
     Issue
    -0.14
     '{"
    -0.14
    held
    -0.14
    jez
    -0.13
     ///<
    -0.13
    stoff
    -0.13
    POSITIVE LOGITS
     points
    0.27
     times
    0.22
     parts
    0.20
    points
    0.20
     Points
    0.20
     moments
    0.19
    -times
    0.18
     certain
    0.18
     certains
    0.17
    .points
    0.17
    Act Density 0.071%

    No Known Activations