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

    Neuronpedia

    INDEX
    Explanations

    references related to dolphins

    oai_token-act-pair · gpt-3.5-turbo

    references to dolphins or related to dolphin contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ablishment
    -0.82
    rade
    -0.74
    Interstitial
    -0.73
    rooms
    -0.71
    ür
    -0.68
    haar
    -0.67
    ãĤ¤ãĥĪ
    -0.67
    ride
    -0.67
     Flavoring
    -0.66
    oppable
    -0.66
    POSITIVE LOGITS
     dolphin
    1.12
     dolphins
    1.04
    iform
    0.86
    arium
    0.82
    olphin
    0.81
    odon
    0.81
    bone
    0.79
     Swim
    0.78
     whale
    0.78
    olphins
    0.77
    Act Density 0.011%

    No Known Activations