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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate highlights or memorable experiences in events and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollen
    -0.17
    antro
    -0.16
    å«Į
    -0.16
     slightest
    -0.16
    _ASSUME
    -0.15
    ityEngine
    -0.15
    ania
    -0.14
    ootball
    -0.14
    duk
    -0.14
    verige
    -0.14
    POSITIVE LOGITS
     highlight
    0.82
     highlights
    0.75
     Highlights
    0.62
     Highlight
    0.58
    highlight
    0.55
    Highlight
    0.51
    Highlights
    0.51
    .highlight
    0.48
    _highlight
    0.47
     highlighted
    0.46
    Act Density 0.194%

    No Known Activations