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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omens
    -0.18
    .makeText
    -0.16
    azzi
    -0.16
    ÑĢел
    -0.16
    agini
    -0.16
     ex
    -0.15
    otas
    -0.15
    bak
    -0.15
    ItemAt
    -0.14
    oday
    -0.14
    POSITIVE LOGITS
     needs
    0.19
     Needs
    0.19
    needs
    0.18
    fore
    0.17
     needed
    0.17
    needed
    0.17
     Needed
    0.16
     weren
    0.16
     aren
    0.16
    Needs
    0.15
    Act Density 0.052%

    No Known Activations