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

    Neuronpedia

    INDEX
    Explanations

    the name "Jona" and "Cardona" across various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term "ona" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulative
    -0.82
    glers
    -0.79
    lings
    -0.78
    lycer
    -0.74
    ty
    -0.72
    liners
    -0.71
    netic
    -0.71
    mask
    -0.70
    best
    -0.70
    regular
    -0.70
    POSITIVE LOGITS
    issance
    1.38
    isance
    1.23
    velength
    1.08
    ire
    0.89
    uthor
    0.87
    ignt
    0.86
    qua
    0.82
    nect
    0.82
    uth
    0.81
    jac
    0.80
    Act Density 0.033%

    No Known Activations