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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer systems and operations

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and time-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ounding
    -0.76
    advertisement
    -0.75
    aeda
    -0.75
    habi
    -0.74
    vana
    -0.73
    raltar
    -0.70
    egu
    -0.69
    MpServer
    -0.69
    asty
    -0.66
    ums
    -0.65
    POSITIVE LOGITS
     they
    1.35
     it
    1.20
     there
    1.15
     we
    1.08
     THEY
    1.03
     nobody
    0.96
     he
    0.93
     she
    0.86
     everybody
    0.84
     you
    0.84
    Act Density 0.490%

    No Known Activations