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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases starting with "there."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.69
     CJ
    -0.58
     cylinders
    -0.58
     stroke
    -0.58
     stricken
    -0.57
     actionGroup
    -0.56
     nib
    -0.55
     coherent
    -0.55
    sed
    -0.54
     Dise
    -0.53
    POSITIVE LOGITS
    abouts
    1.32
    upon
    1.04
    ibaba
    0.83
    after
    0.81
    fore
    0.79
    agons
    0.78
    FORE
    0.76
    enty
    0.75
    ngth
    0.75
    idences
    0.75
    Act Density 0.084%

    No Known Activations