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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating personal preferences or feelings about reading and games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    الحياه
    -0.48
    matchCondition
    -0.42
    ftagPool
    -0.37
     ExecuteAsync
    -0.36
    FirstResponder
    -0.36
    Източници
    -0.36
     Chwiliwch
    -0.36
    eqn
    -0.36
    ✨:
    -0.35
     newArray
    -0.35
    POSITIVE LOGITS
    ſelf
    0.55
    ſelves
    0.54
     myſelf
    0.52
     ſta
    0.52
     diſt
    0.52
     deſt
    0.51
     ſever
    0.50
     deſ
    0.50
     laſt
    0.48
     Diſ
    0.48
    Act Density 1.654%

    No Known Activations