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

    Neuronpedia

    INDEX
    Explanations

    references to actions related to work and contribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sebelumnya
    -0.49
     successively
    -0.47
    σουν
    -0.47
    踏
    -0.47
     successive
    -0.45
     record
    -0.45
     initial
    -0.45
    gnat
    -0.44
     ordem
    -0.44
     озна
    -0.44
    POSITIVE LOGITS
     regularly
    0.93
     routinely
    0.89
     infrequently
    0.85
     graag
    0.83
     frequently
    0.81
     daily
    0.81
     pleaſure
    0.76
    astify
    0.76
     weekly
    0.75
    frequently
    0.74
    Act Density 0.497%

    No Known Activations