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

    Neuronpedia

    INDEX
    Explanations

    references to honoring or showing respect towards something or someone

    oai_token-act-pair · gpt-3.5-turbo

    references to homage, tribute, or opposition in cultural or creative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isen
    -0.48
    gian
    -0.47
    lp
    -0.47
    INC
    -0.47
    _>
    -0.46
    berra
    -0.46
    izoph
    -0.46
    rior
    -0.45
    cade
    -0.44
    975
    -0.44
    POSITIVE LOGITS
     to
    1.57
     thereto
    1.48
    to
    1.21
     TO
    1.12
     To
    1.12
    To
    1.11
     unto
    1.05
     toward
    0.90
     towards
    0.89
    TO
    0.80
    Act Density 0.581%

    No Known Activations