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

    Neuronpedia

    INDEX
    Explanations

    references to past events and comparisons of current states to those events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    verbs or phrases indicating a change or comparison in time

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    icular
    -0.68
    weekly
    -0.68
    eric
    -0.66
    ealous
    -0.66
    aliation
    -0.64
    rick
    -0.63
    ora
    -0.62
    uffy
    -0.61
    entanyl
    -0.61
    ancial
    -0.60
    POSITIVE LOGITS
     lows
    0.85
     predecessors
    0.82
     previous
    0.82
     inception
    0.76
     predecessor
    0.72
     earlier
    0.70
     highs
    0.68
     generations
    0.67
     prior
    0.65
     ancestors
    0.64
    Act Density 0.357%

    No Known Activations