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

    Neuronpedia

    INDEX
    Explanations

    references to gaming mechanics and strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agal
    -0.17
    одав
    -0.16
    ingles
    -0.15
    uze
    -0.15
    atte
    -0.14
    onto
    -0.14
    entr
    -0.14
    imoto
    -0.14
    ÑĨ
    -0.13
    olson
    -0.13
    POSITIVE LOGITS
     classes
    0.22
     Classes
    0.22
     tanker
    0.22
     tank
    0.21
    tank
    0.20
    Classes
    0.20
     subclass
    0.20
    subclass
    0.20
     builds
    0.20
     subclasses
    0.20
    Act Density 0.141%

    No Known Activations