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

    Neuronpedia

    INDEX
    Explanations

    terms related to events, contests, software, programs, exhibitions, and funding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contests, campaigns, and software projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hemy
    -0.78
    wrong
    -0.78
     Wrong
    -0.78
    farious
    -0.73
    Ĭ±
    -0.73
    omething
    -0.70
    Fake
    -0.69
    angering
    -0.67
     careless
    -0.66
    ween
    -0.66
    POSITIVE LOGITS
     consists
    1.74
     comprises
    1.55
     includes
    1.46
     utilizes
    1.44
     contains
    1.39
     consisted
    1.38
     incorporates
    1.29
     revolves
    1.29
     begins
    1.28
     culmin
    1.27
    Act Density 0.478%

    No Known Activations