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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sharing opinions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    locker
    -0.07
    lap
    -0.06
     grav
    -0.06
     respect
    -0.06
    sov
    -0.06
     lap
    -0.06
     Inspir
    -0.06
    Lady
    -0.06
    laps
    -0.05
    Broker
    -0.05
    POSITIVE LOGITS
    utow
    0.07
    into
    0.07
    æŃ
    0.07
    EATURE
    0.07
     share
    0.07
    adaki
    0.07
     disposal
    0.07
    igin
    0.07
    yaw
    0.06
     Pitch
    0.06
    Act Density 0.007%

    No Known Activations