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

    Neuronpedia

    INDEX
    Explanations

    verbs related to rotational movement or change in direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flip" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lod
    -0.78
    ment
    -0.78
     Est
    -0.76
     Advocate
    -0.71
     Ces
    -0.70
    est
    -0.70
     Trib
    -0.70
    ella
    -0.69
    esse
    -0.68
     Mord
    -0.67
    POSITIVE LOGITS
     flip
    3.84
     flips
    2.54
     flipped
    2.44
     flipping
    2.34
     Flip
    2.25
     toss
    1.27
     upside
    1.22
     reverse
    1.22
     swing
    1.13
     tilt
    1.10
    Act Density 0.015%

    No Known Activations