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

    Neuronpedia

    INDEX
    Explanations

    words related to change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    words related to change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLIED
    -0.78
    ©¶æ
    -0.76
     Outdoor
    -0.70
     LIMITED
    -0.69
     Borders
    -0.68
    çĶ°
    -0.67
    RAY
    -0.65
     Antiqu
    -0.64
     COURT
    -0.64
    mia
    -0.64
    POSITIVE LOGITS
     chang
    1.02
    eless
    1.00
    xual
    0.83
    itri
    0.82
    artz
    0.82
    elight
    0.82
    ients
    0.79
    eful
    0.77
    hatt
    0.77
    het
    0.77
    Act Density 0.013%

    No Known Activations