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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events taking effect

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "in effect" or similar expressions indicating the implementation or realization of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDES
    -0.74
    Plot
    -0.69
     Armenia
    -0.67
    ides
    -0.65
    incinn
    -0.64
     Patriarch
    -0.63
    IDE
    -0.63
     Primordial
    -0.62
     Armenian
    -0.62
     Columb
    -0.59
    POSITIVE LOGITS
    uation
    0.92
    uating
    0.90
    uated
    0.87
    lie
    0.86
    ually
    0.84
    iveness
    0.83
    uate
    0.83
    uates
    0.80
    ual
    0.79
    uthor
    0.78
    Act Density 0.012%

    No Known Activations