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

    Neuronpedia

    INDEX
    Explanations

    superlatives related to achievements, rankings, or titles, such as "Most Valuable Player" or "Most Influential Artist."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to rankings or lists of notable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    instead
    -0.73
    icum
    -0.69
    icer
    -0.66
    halla
    -0.66
     Racer
    -0.65
    thur
    -0.64
     Ved
    -0.64
    rompt
    -0.64
    pton
    -0.63
    selves
    -0.61
    POSITIVE LOGITS
     importantly
    0.90
    likely
    0.89
     important
    0.87
     influential
    0.86
     prominent
    0.85
     recognizable
    0.84
     notable
    0.81
     elaborate
    0.81
    afa
    0.79
     egregious
    0.79
    Act Density 0.067%

    No Known Activations