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

    Neuronpedia

    INDEX
    Explanations

    expressions related to filling gaps or vacancies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itchen
    -0.14
    ismet
    -0.14
    .portal
    -0.14
    nton
    -0.14
    toi
    -0.14
    üf
    -0.14
    ureau
    -0.13
     sigmoid
    -0.13
    kinson
    -0.13
    ùi
    -0.13
    POSITIVE LOGITS
     gap
    0.56
     void
    0.56
    gap
    0.52
     gaps
    0.52
     vacuum
    0.48
    void
    0.46
    Gap
    0.46
     Gap
    0.46
    -gap
    0.43
     Void
    0.40
    Act Density 0.064%

    No Known Activations