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

    Neuronpedia

    INDEX
    Explanations

    concepts related to confinement and entrapment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McCart
    -0.15
    ниÑĨ
    -0.14
    ENE
    -0.14
    ixer
    -0.14
     trÃŃ
    -0.14
    581
    -0.13
    OH
    -0.13
    echa
    -0.13
    座
    -0.13
    ollar
    -0.13
    POSITIVE LOGITS
    azor
    0.18
    arty
    0.15
    éijij
    0.15
     Armenian
    0.15
    posables
    0.14
    .Appearance
    0.14
    enge
    0.14
     Opcode
    0.14
    «
    0.14
     fate
    0.14
    Act Density 0.247%

    No Known Activations