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

    Neuronpedia

    INDEX
    Explanations

    keywords related to signs, clues, and evidence

    oai_token-act-pair · gpt-3.5-turbo

    indicators of change or signs in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourses
    -0.75
     concurrently
    -0.69
    ommod
    -0.69
     federation
    -0.68
    OVA
    -0.67
    Ranked
    -0.66
    HQ
    -0.65
    quad
    -0.64
    Private
    -0.64
    eneg
    -0.64
    POSITIVE LOGITS
     clues
    1.06
     Signs
    0.92
     hint
    0.90
     clue
    0.87
     indicating
    0.86
     pointing
    0.83
     ticking
    0.83
    eele
    0.83
     unmist
    0.83
     marker
    0.82
    Act Density 0.676%

    No Known Activations