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

    Neuronpedia

    INDEX
    Explanations

    words related to situations where something is being stretched, pulled, or extended

    oai_token-act-pair · gpt-3.5-turbo

    the word "stray" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.85
     bree
    -0.69
    balls
    -0.64
     Heavenly
    -0.63
    fulness
    -0.62
     grade
    -0.61
     blush
    -0.60
     boo
    -0.59
    mania
    -0.59
     GOODMAN
    -0.59
    POSITIVE LOGITS
    angled
    1.38
    addle
    1.37
    angling
    1.36
    aditional
    1.33
    angle
    1.32
    atum
    1.31
    idently
    1.31
    aining
    1.30
    ategic
    1.27
    ayed
    1.24
    Act Density 0.019%

    No Known Activations