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

    Neuronpedia

    INDEX
    Explanations

    references to community events and public gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    woff
    -0.16
    oice
    -0.15
    osate
    -0.15
    èĴ
    -0.15
    èle
    -0.15
    Ïħγ
    -0.15
     semiclass
    -0.15
     diffs
    -0.14
    ihad
    -0.14
    iced
    -0.14
    POSITIVE LOGITS
     mask
    0.34
     masks
    0.33
     Carnival
    0.31
     masking
    0.31
     mas
    0.31
     masked
    0.31
     Masks
    0.31
     Mask
    0.31
    Mask
    0.29
    mask
    0.29
    Act Density 0.026%

    No Known Activations