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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and statistical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HttpDelete
    -0.75
    onHide
    -0.69
    unregister
    -0.60
    DeleteMapping
    -0.59
     downgrade
    -0.58
    Deactivate
    -0.58
    Minus
    -0.57
     downg
    -0.57
     décro
    -0.56
     teardown
    -0.56
    POSITIVE LOGITS
    InjectAttribute
    0.81
    OGND
    0.73
    IsContent
    0.68
    AsUp
    0.67
     gain
    0.67
    帖最后由
    0.66
     positives
    0.65
     <=",
    0.65
     positive
    0.65
    =+
    0.65
    Act Density 1.115%

    No Known Activations