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

    Neuronpedia

    INDEX
    Explanations

    references to original versions or iterations of items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to "original" and "old" content or concepts across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.87
    ificantly
    -0.75
    ographics
    -0.74
    illation
    -0.73
    %%%%
    -0.72
    urches
    -0.72
    ombs
    -0.72
    haps
    -0.71
    oso
    -0.71
    oppable
    -0.71
    POSITIVE LOGITS
     assumption
    0.90
     era
    0.85
     slate
    0.82
     batch
    0.81
     version
    0.81
     incarnation
    0.80
     occupant
    0.78
     edition
    0.78
     conception
    0.78
     iteration
    0.77
    Act Density 0.096%

    No Known Activations