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

    Neuronpedia

    INDEX
    Explanations

    strong emotional words and physical actions

    oai_token-act-pair · gpt-3.5-turbo

    words that have a "j" sound followed by specific vowel patterns or consonants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.76
    sufficient
    -0.74
    ãĤª
    -0.72
    etheless
    -0.62
     Reps
    -0.62
     srfAttach
    -0.60
     predec
    -0.59
     scarce
    -0.58
    minecraft
    -0.56
    uity
    -0.55
    POSITIVE LOGITS
    neys
    0.94
    ansen
    0.71
     Marriott
    0.70
    ney
    0.69
    lin
    0.68
    anic
    0.67
    dan
    0.66
    ournal
    0.66
    unal
    0.65
    atl
    0.65
    Act Density 0.168%

    No Known Activations