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

    Neuronpedia

    INDEX
    Explanations

    references to input and output parameters or fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eag
    -0.16
    chner
    -0.15
    /is
    -0.15
    appa
    -0.15
    ific
    -0.14
     ae
    -0.14
    uff
    -0.14
     ME
    -0.14
    irt
    -0.14
    iving
    -0.14
    POSITIVE LOGITS
    /output
    0.28
    ted
    0.26
    ting
    0.25
    -output
    0.23
    ters
    0.21
    MethodManager
    0.19
    TING
    0.18
    tsky
    0.17
    thrown
    0.16
    MMdd
    0.15
    Act Density 0.029%

    No Known Activations