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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promotional language or attention-grabbing statements

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "splash."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abiding
    -0.76
    abol
    -0.74
    relevant
    -0.73
    hammad
    -0.71
    elsen
    -0.70
    agan
    -0.69
    ourke
    -0.69
    ravings
    -0.68
    gnu
    -0.67
    relation
    -0.67
    POSITIVE LOGITS
     splash
    1.18
     Splash
    0.99
     ashore
    0.83
    atform
    0.81
    down
    0.78
    pad
    0.76
     Squid
    0.71
    BACK
    0.70
     McKay
    0.70
     Garc
    0.69
    Act Density 0.005%

    No Known Activations