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

    Neuronpedia

    INDEX
    Explanations

    terms related to text encoding and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.83
    ivan
    -0.76
    dale
    -0.71
    owners
    -0.71
    igan
    -0.71
    bottom
    -0.69
    ndra
    -0.68
    ashtra
    -0.67
    iewicz
    -0.66
    inness
    -0.66
    POSITIVE LOGITS
    oded
    1.24
    oding
    1.14
    oder
    1.04
    odes
    0.98
    ode
    0.89
    ryption
    0.88
     encoded
    0.85
     decoding
    0.83
    ãĥĥãĥī
    0.82
     encoding
    0.82
    Act Density 0.136%

    No Known Activations