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

    Neuronpedia

    INDEX
    Explanations

    conditional and temporal statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Confucius
    -0.75
     Cæsar
    -0.69
    ſelf
    -0.67
     Viter
    -0.66
     Pelop
    -0.65
     Schengen
    -0.64
    ſelves
    -0.63
     Esau
    -0.63
     Mahler
    -0.61
     houſe
    -0.60
    POSITIVE LOGITS
     the
    0.99
     we
    0.91
     it
    0.90
     they
    0.87
     there
    0.73
    assertThat
    0.73
     he
    0.71
     you
    0.71
     these
    0.70
     our
    0.70
    Act Density 0.344%

    No Known Activations