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

    Neuronpedia

    INDEX
    Explanations

    words related to size or quantity, particularly emphasizing bigness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to size, height, and intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Divinity
    -0.71
    itle
    -0.69
    cend
    -0.67
    ellectual
    -0.66
    oute
    -0.65
    vous
    -0.65
    ITNESS
    -0.64
    ocratic
    -0.63
    apter
    -0.63
    orial
    -0.61
    POSITIVE LOGITS
     enough
    1.31
    enough
    1.10
    aneously
    1.01
    heartedly
    0.97
    handedly
    0.96
     Enough
    0.82
     asleep
    0.78
    balls
    0.76
     amounts
    0.75
    etheless
    0.75
    Act Density 0.252%

    No Known Activations