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

    Neuronpedia

    INDEX
    Explanations

    the word "nothing" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agli
    -0.16
    SEA
    -0.15
    mont
    -0.14
    Globals
    -0.14
    ãĥ¼ãĥģ
    -0.14
     anything
    -0.14
    assing
    -0.14
     Freed
    -0.14
     optarg
    -0.14
    WAY
    -0.14
    POSITIVE LOGITS
    ness
    0.24
     else
    0.20
    burger
    0.18
    else
    0.17
    epad
    0.17
    NESS
    0.15
    Else
    0.15
    ride
    0.15
    rane
    0.15
    idia
    0.14
    Act Density 0.025%

    No Known Activations