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

    Neuronpedia

    INDEX
    Explanations

    phrases related to indirect effects or connections

    oai_token-act-pair · gpt-3.5-turbo

    references to indirect effects or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.80
    ikers
    -0.79
    Crunch
    -0.78
    azines
    -0.76
    erk
    -0.76
    awar
    -0.73
    frey
    -0.73
    avers
    -0.72
    pecting
    -0.71
    Dur
    -0.71
    POSITIVE LOGITS
     indirect
    1.16
    irect
    0.85
     intermediary
    0.81
     imped
    0.76
     winding
    0.74
     coupling
    0.73
     illumination
    0.73
     relations
    0.72
     sidel
    0.71
     reflection
    0.71
    Act Density 0.005%

    No Known Activations