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

    Neuronpedia

    INDEX
    Explanations

    programming-related expressions and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hang
    -0.16
     Halk
    -0.15
    877
    -0.15
    814
    -0.15
    eld
    -0.15
    .pick
    -0.15
     sheer
    -0.15
    e
    -0.14
    oa
    -0.14
    ine
    -0.14
    POSITIVE LOGITS
    oreach
    0.19
    é¦
    0.18
    adow
    0.17
    HEME
    0.16
    rowse
    0.16
    mpz
    0.14
    erset
    0.14
    ignon
    0.14
    andez
    0.14
    apist
    0.14
    Act Density 0.093%

    No Known Activations