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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting a sequence of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.78
    lees
    -0.72
     Franch
    -0.68
    ux
    -0.66
    balls
    -0.66
     Including
    -0.63
    agar
    -0.63
    ibu
    -0.61
     Lauder
    -0.60
    tics
    -0.60
    POSITIVE LOGITS
     step
    1.08
     generation
    0.99
     iteration
    0.99
     closest
    0.98
     logical
    0.97
     installment
    0.96
     phase
    0.91
     paragraph
    0.89
     chapter
    0.89
     thing
    0.86
    Act Density 0.021%

    No Known Activations