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

    Neuronpedia

    INDEX
    Explanations

    references to games or gameplay elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erot
    -0.18
    adx
    -0.16
    eman
    -0.16
    invert
    -0.16
    erap
    -0.15
    294
    -0.15
    trys
    -0.15
     Rena
    -0.15
     qualified
    -0.14
    451
    -0.14
    POSITIVE LOGITS
    ground
    0.28
    grounds
    0.27
    thing
    0.26
    fulness
    0.26
    time
    0.23
    mates
    0.23
    GROUND
    0.22
    pen
    0.22
    ful
    0.22
    Ground
    0.22
    Act Density 0.013%

    No Known Activations