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

    Neuronpedia

    INDEX
    Explanations

    phrases related to saving or preservation

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "saving" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     threaded
    -0.72
     matching
    -0.66
     Turing
    -0.63
     tapping
    -0.63
     stool
    -0.62
     tubing
    -0.61
     marijuana
    -0.59
     distributor
    -0.59
     tap
    -0.59
     sil
    -0.59
    POSITIVE LOGITS
    iour
    1.70
    annah
    1.41
    vy
    1.37
    inelli
    1.30
    iors
    1.29
    vier
    1.24
    oir
    1.21
    ouring
    1.12
    chenko
    1.10
    oy
    1.07
    Act Density 0.030%

    No Known Activations