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

    Neuronpedia

    INDEX
    Explanations

    terms related to enhancements, expansions, and increases

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating improvements or enhancements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.82
    Ĭ
    -0.80
    ices
    -0.79
    į
    -0.79
    Į
    -0.78
    coins
    -0.75
    oused
    -0.73
    wered
    -0.72
    İ
    -0.72
    Ĥ
    -0.72
    POSITIVE LOGITS
     version
    0.97
     versions
    0.91
     edition
    0.80
     scrutiny
    0.79
     embodiment
    0.76
     capability
    0.72
     interrogation
    0.72
     susceptibility
    0.72
     bargaining
    0.71
     attention
    0.71
    Act Density 0.122%

    No Known Activations