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

    Neuronpedia

    INDEX
    Explanations

    mentions of a personal creation or project

    oai_token-act-pair · gpt-3.5-turbo

    the repeated reference to 'this' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isms
    -0.78
    aws
    -0.78
    ©¶æ¥µ
    -0.76
    ¨
    -0.73
    planes
    -0.72
    ãĤ¹ãĥĪ
    -0.71
    rors
    -0.71
    Ĭ±
    -0.70
    Ľ
    -0.70
    ãĥĥ
    -0.70
    POSITIVE LOGITS
     particular
    0.94
     trope
    0.90
     sucker
    0.86
     newfound
    0.83
     guy
    0.83
     week
    0.82
     information
    0.81
     happen
    0.81
     nifty
    0.79
     latest
    0.79
    Act Density 0.175%

    No Known Activations