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

    Neuronpedia

    INDEX
    Explanations

    variables and functions related to mathematical equations and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Samuel
    -0.17
    ī
    -0.17
    131
    -0.15
    <[
    -0.15
     alike
    -0.15
    hoff
    -0.15
    avana
    -0.14
    ogo
    -0.14
    assage
    -0.13
     Alleg
    -0.13
    POSITIVE LOGITS
     Amy
    0.42
    _\
    0.41
     amy
    0.39
    Amy
    0.38
     Primitive
    0.30
     primitive
    0.28
    AMY
    0.28
     np
    0.27
    amy
    0.26
    =np
    0.25
    Act Density 0.041%

    No Known Activations