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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or connection with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.87
     purpoſe
    -0.86
     Cæsar
    -0.84
     Majefty
    -0.79
     Sarm
    -0.79
     ſche
    -0.77
     Houſe
    -0.74
     ſtate
    -0.74
     Efq
    -0.73
     ftate
    -0.70
    POSITIVE LOGITS
     the
    1.06
     With
    0.92
     a
    0.91
     with
    0.88
     some
    0.86
    +
    0.84
     WITH
    0.84
     Avec
    0.83
     accompanying
    0.82
    companying
    0.81
    Act Density 0.034%

    No Known Activations