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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evidence or indication

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conclusions or implications about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pictured
    -0.65
     revelations
    -0.64
    Synopsis
    -0.62
     reminds
    -0.61
    mentioned
    -0.60
     recounted
    -0.60
    ibrary
    -0.59
    aughs
    -0.59
    eddy
    -0.58
     accuses
    -0.58
    POSITIVE LOGITS
     indeed
    1.23
     considerably
    0.79
     substantially
    0.77
     definitely
    0.77
     disproportion
    0.76
     genuinely
    0.76
     remarkably
    0.76
     intended
    0.74
     quite
    0.74
     genuine
    0.74
    Act Density 0.546%

    No Known Activations