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

    Neuronpedia

    INDEX
    Explanations

    references to age and childhood-related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     مشين
    -0.65
     whoſe
    -0.59
    ParallelGroup
    -0.58
    ContentAsync
    -0.57
    mergeFrom
    -0.57
     Theſe
    -0.55
     Jusqu
    -0.54
    MessageWindow
    -0.54
     nocturna
    -0.54
     kinderg
    -0.53
    POSITIVE LOGITS
    ambique
    0.54
    bolista
    0.53
    openhauer
    0.52
    στα
    0.51
     Lumpur
    0.50
    tanooga
    0.50
    ldorf
    0.50
     Reg
    0.49
    lacion
    0.49
    pellier
    0.49
    Act Density 0.030%

    No Known Activations