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

    Neuronpedia

    INDEX
    Explanations

    instances where something is being extended or expanded

    oai_token-act-pair · gpt-3.5-turbo

    references to extending rights or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fighter
    -0.76
    Submit
    -0.76
    «
    -0.74
    ches
    -0.73
    lean
    -0.73
    kie
    -0.71
    idd
    -0.71
    ids
    -0.69
    idding
    -0.69
    leck
    -0.69
    POSITIVE LOGITS
     adolesc
    0.99
     warranties
    0.91
    ITED
    0.81
    ENDED
    0.79
     lifespan
    0.76
     cords
    0.76
    ISS
    0.72
    ibility
    0.70
     cord
    0.70
     condolences
    0.70
    Act Density 0.036%

    No Known Activations