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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical or quantum theories and their terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EVALU
    -0.82
    distribute
    -0.81
    EVALU
    -0.81
     distribute
    -0.79
     Deploy
    -0.77
    Inspect
    -0.76
    Integrating
    -0.76
    Evaluating
    -0.75
     calibrate
    -0.74
     Distribute
    -0.74
    POSITIVE LOGITS
     modification
    0.73
    idation
    0.70
    ization
    0.70
    oration
    0.69
     alteration
    0.69
    ulation
    0.68
     inhibition
    0.68
    cipation
    0.68
    INATION
    0.68
    imation
    0.67
    Act Density 1.392%

    No Known Activations