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

    Neuronpedia

    INDEX
    Explanations

    references to mountains and related geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſte
    -0.45
     Majefty
    -0.43
     Inſ
    -0.42
    vician
    -0.42
     Diſ
    -0.41
     Cien
    -0.39
     Reſ
    -0.39
     Monfieur
    -0.37
     pleaſure
    -0.36
    헌
    -0.35
    POSITIVE LOGITS
     mount
    0.80
    mt
    0.70
    mount
    0.69
     Mount
    0.62
     mt
    0.61
    MOUNT
    0.60
    Mount
    0.60
    MT
    0.57
     MOUNT
    0.57
     mounts
    0.56
    Act Density 0.383%

    No Known Activations