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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or exclamation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iros
    -0.17
    ENTA
    -0.15
    inent
    -0.15
    лини
    -0.14
    _VEC
    -0.14
    lined
    -0.14
    agli
    -0.14
    icipation
    -0.14
    θμ
    -0.14
     automát
    -0.13
    POSITIVE LOGITS
    rob
    0.14
    館
    0.14
    blem
    0.14
    atee
    0.14
     unto
    0.14
    ÑĮе
    0.13
    phabet
    0.13
     reg
    0.13
    asks
    0.13
    -UA
    0.13
    Act Density 0.013%

    No Known Activations