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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or adverse conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding suffixes like "ation", "ment", or "rated"

    np_acts-logits-general · gemini-2.0-flash

    operation, development, rated, ment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.77
     fevere
    -0.70
     stiefel
    -0.69
     pleaſure
    -0.68
     itſelf
    -0.68
     raiſ
    -0.67
     Efq
    -0.67
     uſed
    -0.67
     Majefty
    -0.67
     ſtand
    -0.66
    POSITIVE LOGITS
    UnusedPrivate
    0.59
    PerformLayout
    0.55
    EndInit
    0.50
    ]")]
    0.49
    IContainer
    0.49
    SequentialGroup
    0.49
    TagMode
    0.48
    providedIn
    0.45
    HtmlAttribute
    0.45
    ]),
    0.44
    Act Density 0.084%

    No Known Activations