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

    Neuronpedia

    INDEX
    Explanations

    phrases related to brevity or concise descriptions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "brief" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceans
    -0.71
    Queen
    -0.68
     Polo
    -0.68
    Drive
    -0.66
    SEA
    -0.65
    çĶ°
    -0.65
    IVER
    -0.64
    artifacts
    -0.62
    GREEN
    -0.61
    CE
    -0.60
    POSITIVE LOGITS
    cases
    1.33
    case
    1.30
    itud
    0.87
    erate
    0.84
    itude
    0.83
     glimps
    0.81
    er
    0.80
    ebin
    0.79
    est
    0.79
     periods
    0.76
    Act Density 0.020%

    No Known Activations