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

    Neuronpedia

    INDEX
    Explanations

    the occurrences of the word "Santa"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.90
     pleaſure
    -0.84
     Monfieur
    -0.80
     poffible
    -0.79
     himſelf
    -0.78
     ſeveral
    -0.78
     Jefus
    -0.77
     themſelves
    -0.76
     ſever
    -0.75
     ་་
    -0.74
    POSITIVE LOGITS
     its
    0.69
     spatial
    0.68
    LookAnd
    0.63
     spot
    0.62
     Spot
    0.62
     St
    0.61
     the
    0.58
     Santa
    0.58
    Spot
    0.58
    LikeLike
    0.57
    Act Density 0.111%

    No Known Activations