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

    Neuronpedia

    INDEX
    Explanations

    words related to magnitude or importance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "order of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gow
    -0.99
    nis
    -0.74
    iov
    -0.72
    lees
    -0.71
    atform
    -0.71
    ished
    -0.68
    runtime
    -0.67
    mouth
    -0.66
    nih
    -0.65
    iland
    -0.63
    POSITIVE LOGITS
     magnitude
    1.12
     precedence
    0.98
     descent
    0.70
    rontal
    0.69
    aiden
    0.68
     priority
    0.66
     preference
    0.65
     elimination
    0.64
     multiplication
    0.62
     anarchy
    0.62
    Act Density 0.117%

    No Known Activations