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

    Neuronpedia

    INDEX
    Explanations

    quantifiable changes and statistics related to populations and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bjerg
    -0.16
    ustr
    -0.15
    à¸Ħว
    -0.15
     outward
    -0.14
    uries
    -0.14
    .Void
    -0.14
     itching
    -0.14
    quier
    -0.13
     hak
    -0.13
    StateManager
    -0.13
    POSITIVE LOGITS
     to
    0.37
    åĪ°
    0.34
    èĩ³
    0.31
     Ø¥ÙĦÙī
    0.27
     åĪ°
    0.27
    åĪ°äºĨ
    0.26
     èĩ³
    0.23
    ToOne
    0.23
     down
    0.23
     до
    0.22
    Act Density 0.175%

    No Known Activations