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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Martin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĥ½
    -2.13
     '$
    -1.91
    ¬
    -1.83
    ?”
    -1.72
    ¿½
    -1.70
    Ģ
    -1.69
    ?_
    -1.62
     _________
    -1.61
    "?
    -1.61
    ?"
    -1.60
    POSITIVE LOGITS
    pora
    2.06
    cule
    1.96
    ique
    1.94
    cules
    1.79
    idone
    1.76
    dale
    1.74
    dorff
    1.74
    ico
    1.73
    boro
    1.71
    culo
    1.69
    Act Density 0.016%

    No Known Activations