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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture

    oai_token-act-pair · gpt-3.5-turbo

    terms related to architecture and related fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivism
    -0.98
    ocrates
    -0.79
    lain
    -0.79
    etts
    -0.78
    ress
    -0.78
    rays
    -0.77
    ertodd
    -0.76
    eus
    -0.75
    rosis
    -0.74
    ritis
    -0.74
    POSITIVE LOGITS
     competence
    0.89
     representations
    0.81
     impossibility
    0.81
     activity
    0.79
     objections
    0.79
     referen
    0.78
     prowess
    0.78
     achievements
    0.78
     landmarks
    0.76
     significance
    0.76
    Act Density 0.035%

    No Known Activations