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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or important subjects in a discussion

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <bos>
    -0.62
     Agamemnon
    -0.52
     chagrin
    -0.52
     Phry
    -0.50
     Phoen
    -0.49
     Pharaoh
    -0.49
     nukes
    -0.48
     Tbilisi
    -0.48
    try
    -0.48
     condoms
    -0.47
    POSITIVE LOGITS
     this
    1.21
     these
    1.21
     THESE
    1.13
    These
    1.12
     THIS
    1.11
     These
    1.10
    THIS
    1.10
     particular
    1.05
    "):
    1.04
     deste
    1.03
    Act Density 1.337%

    No Known Activations