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

    Neuronpedia

    INDEX
    Explanations

    mentions of dolphins

    oai_token-act-pair · gpt-3.5-turbo

    references to dolphins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eners
    -0.85
    ablishment
    -0.82
    rooms
    -0.81
    ãĤ¤ãĥĪ
    -0.71
    rade
    -0.70
    ãĥ´ãĤ¡
    -0.70
    ride
    -0.67
    istries
    -0.65
    ielding
    -0.65
    cation
    -0.63
    POSITIVE LOGITS
     dolphin
    0.92
    iform
    0.83
    arium
    0.81
     dolphins
    0.77
    patch
    0.74
     Seal
    0.70
    bone
    0.70
    odon
    0.69
    agraph
    0.68
     Swim
    0.68
    Act Density 0.029%

    No Known Activations