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

    Neuronpedia

    INDEX
    Explanations

    descriptions of artistic and professional practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     worked
    -0.19
    aret
    -0.15
    worked
    -0.14
     consisting
    -0.14
    rade
    -0.14
    Brief
    -0.14
    visor
    -0.14
    elta
    -0.14
    ENO
    -0.14
     want
    -0.14
    POSITIVE LOGITS
     span
    0.33
     range
    0.29
     str
    0.29
     crosses
    0.28
     ranges
    0.28
     ranged
    0.27
     touch
    0.26
     spans
    0.25
    span
    0.25
    -cross
    0.25
    Act Density 0.123%

    No Known Activations