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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LINE
    -0.59
    legraph
    -0.58
    edia
    -0.54
     Cipher
    -0.54
     juggling
    -0.54
    IDENT
    -0.54
     rapists
    -0.54
    Cy
    -0.54
     Cascade
    -0.53
     robber
    -0.53
    POSITIVE LOGITS
    nam
    1.08
    nery
    1.04
    chard
    1.02
    leans
    0.98
    lando
    0.94
    acular
    0.90
    acles
    0.89
    gin
    0.87
    acle
    0.86
    phan
    0.86
    Act Density 0.013%

    No Known Activations