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

    Neuronpedia

    INDEX
    Explanations

    elements related to the organization and content structure of written documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jev
    -0.16
    jav
    -0.15
    ito
    -0.14
    .Dom
    -0.14
    igo
    -0.14
    obra
    -0.14
     Cheat
    -0.14
    views
    -0.14
    Injection
    -0.14
    _ALT
    -0.13
    POSITIVE LOGITS
     contain
    0.18
     contains
    0.18
    bj
    0.18
    ucz
    0.16
    Verdana
    0.15
    contains
    0.15
    contain
    0.15
     principal
    0.15
    alara
    0.15
     features
    0.15
    Act Density 0.453%

    No Known Activations