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

    Neuronpedia

    INDEX
    Explanations

    phrases related to innovation and novelty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoe
    -0.83
    SHIP
    -0.81
    eph
    -0.71
    ashtra
    -0.71
     NETWORK
    -0.66
    vana
    -0.65
    utterstock
    -0.65
     DRAG
    -0.64
    igraph
    -0.63
    RPG
    -0.62
    POSITIVE LOGITS
     improved
    0.92
    leans
    0.92
     inexperienced
    0.92
     unfamiliar
    0.91
     refreshed
    0.87
     unexpl
    0.83
     renovated
    0.79
     unforeseen
    0.79
     inventive
    0.79
     exciting
    0.79
    Act Density 0.178%

    No Known Activations