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

    Neuronpedia

    INDEX
    Explanations

    references to hierarchical structures and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    شهاد
    -0.62
     ."
    -0.59
     .”
    -0.58
    ."'
    -0.57
    ‟
    -0.56
    vejte
    -0.56
     sahiptir
    -0.54
     étrangère
    -0.54
     lecz
    -0.53
    」
    -0.52
    POSITIVE LOGITS
     IIRC
    1.23
     iirc
    1.09
     AFA
    0.99
     (!)
    0.94
    ...)
    0.93
    (!)
    0.92
     OTO
    0.92
     IMHO
    0.89
    FWIW
    0.88
     (~
    0.87
    Act Density 1.431%

    No Known Activations