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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning numbers

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" across various contexts in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.82
    ORPG
    -0.81
    Deal
    -0.74
    ãĤ¤ãĥĪ
    -0.73
    apons
    -0.73
    amily
    -0.72
    izards
    -0.71
    cycles
    -0.70
    IUM
    -0.70
    ubi
    -0.66
    POSITIVE LOGITS
     final
    1.41
     foremost
    1.40
     last
    1.21
     longest
    1.20
     fourth
    1.20
     seventh
    1.19
     third
    1.18
     fifth
    1.16
     sixth
    1.16
     simplest
    1.12
    Act Density 0.070%

    No Known Activations