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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Guna
    -0.09
    ILLISECONDS
    -0.09
    REA
    -0.09
    eward
    -0.08
    cak
    -0.08
    ofday
    -0.08
    obo
    -0.08
    AdapterFactory
    -0.08
    etti
    -0.08
    etten
    -0.08
    POSITIVE LOGITS
    /high
    0.06
     Coleman
    0.05
    imate
    0.05
     pinned
    0.05
    wh
    0.05
     Bom
    0.05
     hell
    0.05
    z
    0.05
     natural
    0.05
     Pin
    0.05
    Act Density 0.002%

    No Known Activations