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

    Neuronpedia

    INDEX
    Explanations

    words related to control, direction, or dominance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obstacles or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.64
    Ń·
    -0.60
    zbek
    -0.59
    Ô
    -0.59
    ¿½
    -0.57
    vae
    -0.57
    ccording
    -0.56
     Hass
    -0.56
     Worldwide
    -0.55
     Marketable
    -0.53
    POSITIVE LOGITS
    iest
    1.17
    liest
    0.80
     throne
    0.71
    osphere
    0.70
    hest
    0.69
    ultimate
    0.68
     aisle
    0.68
    antry
    0.67
     tray
    0.66
     basket
    0.65
    Act Density 0.649%

    No Known Activations