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

    Neuronpedia

    INDEX
    Explanations

    references to procedures and instructions involving the use of specific items or variables in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.61
    ensement
    -0.49
     définiti
    -0.47
     mostrarán
    -0.47
    oneofs
    -0.46
    তথ্যসূত্র
    -0.45
     roulant
    -0.44
     décédé
    -0.44
     olmak
    -0.43
     Yet
    -0.43
    POSITIVE LOGITS
    esModule
    0.68
    UnsafeEnabled
    0.66
    BufferException
    0.59
    ftagPool
    0.58
     Shakspeare
    0.58
     rospy
    0.58
     daim
    0.58
     ✭✭
    0.57
    ηγ
    0.57
    himovic
    0.57
    Act Density 0.796%

    No Known Activations