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

    Neuronpedia

    INDEX
    Explanations

    references to specific technical terms and statistical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffance
    -0.87
     sánchez
    -0.86
     lópez
    -0.80
     rodríguez
    -0.79
     gonzález
    -0.78
    avelength
    -0.72
     meriva
    -0.72
    iterranée
    -0.69
     abbildung
    -0.68
     kapture
    -0.68
    POSITIVE LOGITS
    <bos>
    1.43
    nip
    0.73
    cyc
    0.73
    butt
    0.71
    orb
    0.70
    luc
    0.69
    hob
    0.69
    imm
    0.69
    fork
    0.68
    Berg
    0.68
    Act Density 6.444%

    No Known Activations