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

    Neuronpedia

    INDEX
    Explanations

    instances of personal research and exploration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isci
    -0.17
    edback
    -0.14
     Transcript
    -0.14
    kke
    -0.14
    /trunk
    -0.13
    kad
    -0.13
    indi
    -0.13
    važ
    -0.13
    iddi
    -0.13
    ocker
    -0.12
    POSITIVE LOGITS
     google
    0.58
     Google
    0.56
     research
    0.53
    Google
    0.50
    google
    0.50
     goog
    0.49
     GOOGLE
    0.48
    .google
    0.46
     researching
    0.46
    research
    0.44
    Act Density 0.410%

    No Known Activations