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

    Neuronpedia

    INDEX
    Explanations

    terms associated with physical structures or locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĹ
    -0.81
    itans
    -0.70
    OY
    -0.69
    izoph
    -0.69
    vez
    -0.69
    Mos
    -0.68
    Gam
    -0.68
    IJ
    -0.66
    Ak
    -0.65
    ¥
    -0.65
    POSITIVE LOGITS
     containing
    0.90
    aneously
    0.77
     cascade
    0.76
    ful
    0.74
    ment
    0.74
    ishly
    0.74
     wherein
    0.74
     overflow
    0.72
     consisting
    0.71
     charm
    0.71
    Act Density 0.510%

    No Known Activations