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

    Neuronpedia

    INDEX
    Explanations

    references to spherical objects

    oai_token-act-pair · gpt-3.5-turbo

    references to physical spherical objects, particularly in a experimental or playful context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´
    -0.71
    EMBER
    -0.70
    quished
    -0.69
    yles
    -0.63
     Flickr
    -0.63
    Marginal
    -0.63
     effic
    -0.61
    atalie
    -0.61
    States
    -0.60
    raints
    -0.59
    POSITIVE LOGITS
    ball
    1.00
    balls
    0.98
     balls
    0.92
    wagen
    0.91
    buster
    0.90
    gb
    0.81
     Balls
    0.79
    asma
    0.79
    olicited
    0.78
    wing
    0.77
    Act Density 0.027%

    No Known Activations