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

    Neuronpedia

    INDEX
    Explanations

    news headlines with urgent calls to action

    oai_token-act-pair · gpt-3.5-turbo

    urgent requests or recommendations for viewing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.72
     Cantor
    -0.71
     fortun
    -0.70
     Schwar
    -0.68
     Phant
    -0.65
     rall
    -0.65
     Mig
    -0.64
     Bri
    -0.64
     Lauder
    -0.63
     Pilgrim
    -0.63
    POSITIVE LOGITS
     WATCH
    1.24
    ARD
    0.83
    ANG
    0.76
    ENS
    0.72
    AUD
    0.72
    INAL
    0.71
    IFF
    0.70
    ached
    0.70
    LECT
    0.69
    OSE
    0.69
    Act Density 0.004%

    No Known Activations