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

    Neuronpedia

    INDEX
    Explanations

    dates and temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dagen
    -0.52
    ModelAdmin
    -0.49
    ന്ന
    -0.48
    Only
    -0.48
    Tage
    -0.47
     MOMENT
    -0.47
     tối
    -0.46
    yip
    -0.46
    ident
    -0.45
    tellt
    -0.44
    POSITIVE LOGITS
    ########.
    0.79
    TagMode
    0.79
     GenerationType
    0.77
    niająca
    0.76
     snippetHide
    0.74
    tanleria
    0.67
    didSet
    0.67
    ]`
    0.66
    addGap
    0.65
    CloseOperation
    0.65
    Act Density 0.136%

    No Known Activations