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

    Neuronpedia

    INDEX
    Explanations

    phrases or single words related to collecting data or items

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to collecting or gathering information and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    numbered
    -0.78
    facing
    -0.74
    agate
    -0.74
    forth
    -0.72
    addin
    -0.72
    ovy
    -0.69
    tty
    -0.67
    seek
    -0.62
    izon
    -0.61
    SourceFile
    -0.61
    POSITIVE LOGITS
    DragonMagazine
    0.82
     dues
    0.81
     fragments
    0.79
     signatures
    0.77
     souven
    0.75
     leftover
    0.74
    abytes
    0.72
     fragmented
    0.72
     tid
    0.70
     clues
    0.70
    Act Density 0.195%

    No Known Activations