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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a source or origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramer
    -0.17
    terms
    -0.17
    lah
    -0.15
    rego
    -0.15
    odos
    -0.14
    ITCH
    -0.13
    getSingleton
    -0.13
    ãģ°
    -0.13
    reating
    -0.13
    ilib
    -0.13
    POSITIVE LOGITS
    /to
    0.30
    /by
    0.20
     scratch
    0.18
    /about
    0.18
     laut
    0.16
    alto
    0.16
    oir
    0.15
     vá»±
    0.14
    age
    0.14
    hell
    0.14
    Act Density 0.306%

    No Known Activations