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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    auga
    -0.16
    YE
    -0.14
    orro
    -0.14
    iska
    -0.14
    ADI
    -0.14
     hrom
    -0.14
    моÑĤ
    -0.14
    arma
    -0.13
    orrow
    -0.13
    POSITIVE LOGITS
    strings
    0.22
    github
    0.19
    math
    0.18
     github
    0.18
    "github
    0.18
    encoding
    0.18
    reflect
    0.17
     math
    0.17
     strings
    0.16
    log
    0.16
    Act Density 0.007%

    No Known Activations