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

    Neuronpedia

    INDEX
    Explanations

    terms related to advanced detection technologies and their capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mith
    -0.19
    Unchecked
    -0.17
    illas
    -0.17
    aux
    -0.14
    ίÏīν
    -0.14
    äºĪ
    -0.14
    (mut
    -0.14
    jen
    -0.14
    åĬĽéĩı
    -0.13
     italic
    -0.13
    POSITIVE LOGITS
     presence
    0.20
     changes
    0.18
    Presence
    0.18
    presence
    0.18
     Presence
    0.17
     status
    0.17
    Changes
    0.17
     discrim
    0.16
     Invisible
    0.16
     whether
    0.16
    Act Density 0.146%

    No Known Activations