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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to sensory characteristics or physical appearance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disabilities and sensitivity to others' conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ameron
    -0.66
    Additional
    -0.62
    lag
    -0.61
    Wo
    -0.61
    Ball
    -0.60
     Sierra
    -0.60
    Western
    -0.59
    ggles
    -0.58
    initions
    -0.58
    UTION
    -0.58
    POSITIVE LOGITS
     enough
    0.96
     minded
    0.77
    retty
    0.75
    ãĥ¼ãĤ¯
    0.67
    enough
    0.66
     asleep
    0.65
     Ichigo
    0.65
    urated
    0.65
    wired
    0.65
     alright
    0.64
    Act Density 0.497%

    No Known Activations