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

    Neuronpedia

    INDEX
    Explanations

    phrases related to flipping, both literally and metaphorically

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "flip" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.82
    ALLY
    -0.69
     EntityItem
    -0.69
    FORE
    -0.69
    mble
    -0.67
     pains
    -0.66
    AMI
    -0.66
    ridor
    -0.65
    needs
    -0.63
    aph
    -0.63
    POSITIVE LOGITS
     flo
    1.00
    olitics
    1.00
     burgers
    0.96
     flipped
    0.92
    tera
    0.90
     flips
    0.89
    flo
    0.85
     flip
    0.80
     flipping
    0.80
     sides
    0.78
    Act Density 0.033%

    No Known Activations