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

    Neuronpedia

    INDEX
    Explanations

    terms related to frameworks or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to structural systems or plans in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dream
    -0.79
    inel
    -0.73
    hib
    -0.72
    rooms
    -0.71
    pi
    -0.71
    cial
    -0.71
    igi
    -0.70
    azar
    -0.68
    vag
    -0.65
    rey
    -0.65
    POSITIVE LOGITS
     framework
    1.06
    framework
    0.81
     frameworks
    0.78
     Framework
    0.72
     guidelines
    0.72
    arity
    0.71
     initialized
    0.69
     builder
    0.68
     guideline
    0.65
     principles
    0.65
    Act Density 0.021%

    No Known Activations