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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a call to action or directive

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate personal experiences or perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGR
    -0.83
    OSP
    -0.70
    UA
    -0.63
    gd
    -0.62
    act
    -0.62
    emis
    -0.61
     Forums
    -0.60
    EO
    -0.60
    OFF
    -0.59
    Ire
    -0.59
    POSITIVE LOGITS
     yourselves
    1.09
     yourself
    0.92
    Tube
    0.70
     gotta
    0.69
     your
    0.67
     mileage
    0.67
     need
    0.66
     shalt
    0.64
     Tube
    0.64
    anchester
    0.62
    Act Density 0.276%

    No Known Activations