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

    Neuronpedia

    INDEX
    Explanations

    specific scientific or technical terminology related to various fields, including medicine and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ヒ
    -0.44
    ヒ
    -0.41
    hurt
    -0.40
     Hir
    -0.39
     незавершена
    -0.39
     Hugh
    -0.36
    Hir
    -0.35
     Hü
    -0.35
    Hugh
    -0.35
    hor
    -0.35
    POSITIVE LOGITS
     ha
    2.75
     Ha
    2.44
    Ha
    2.31
    ha
    2.19
     HA
    2.09
    HA
    1.95
     Hap
    1.73
     Ха
    1.66
     Hag
    1.65
     ха
    1.61
    Act Density 2.079%

    No Known Activations