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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong positive evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldo
    -0.18
    tees
    -0.16
    at
    -0.16
    elli
    -0.16
    eum
    -0.15
    elight
    -0.15
    nal
    -0.15
    ofile
    -0.15
    yen
    -0.15
    ziel
    -0.14
    POSITIVE LOGITS
    spring
    0.21
    ington
    0.19
    못
    0.19
    ows
    0.19
    -known
    0.18
     enough
    0.17
    akit
    0.17
    acre
    0.17
    ender
    0.16
    iam
    0.16
    Act Density 0.054%

    No Known Activations