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

    Neuronpedia

    INDEX
    Explanations

    mentioned issues and problems in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to operational problems and shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erenn
    -0.76
    amous
    -0.76
    Terror
    -0.74
    ombies
    -0.72
    ombie
    -0.72
    riots
    -0.70
    augh
    -0.69
    idal
    -0.69
    bern
    -0.69
    forts
    -0.68
    POSITIVE LOGITS
     wiring
    1.04
     handling
    1.02
     processing
    0.92
     rollout
    0.89
     interpreting
    0.88
     calibration
    0.87
     pacing
    0.87
     transmission
    0.84
     communication
    0.83
     ventilation
    0.83
    Act Density 0.318%

    No Known Activations