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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explanations or justifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe concepts, reasoning, and evaluations of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.93
    ãģ®éŃĶ
    -0.73
    Reviewer
    -0.71
    externalActionCode
    -0.71
    Engineers
    -0.68
    Scotland
    -0.67
    CLOSE
    -0.67
    SHARE
    -0.66
    earchers
    -0.65
    Jews
    -0.64
    POSITIVE LOGITS
     these
    1.33
     this
    1.25
    these
    1.04
     such
    0.96
    this
    0.81
     causation
    0.78
     THIS
    0.77
     THESE
    0.71
     caus
    0.71
     LW
    0.69
    Act Density 0.651%

    No Known Activations