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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "over."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    punk
    -1.54
     Patri
    -1.49
    esis
    -1.44
     femin
    -1.43
     reb
    -1.37
    Rev
    -1.35
     negot
    -1.33
    rendum
    -1.31
     dyst
    -1.29
     pro
    -1.28
    POSITIVE LOGITS
    »¿
    4.15
    ±
    3.48
    ½
    3.44
    ´
    3.36
      ↵
    3.31
    3.31
    ↵↵
    3.31
    3.31
    ↵
    3.31
    3.31
    Act Density 0.213%

    No Known Activations