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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest cause and effect relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.87
     pleaſure
    -0.86
     myſelf
    -0.85
     Monfieur
    -0.85
     purpoſe
    -0.84
     Theſe
    -0.82
     Efq
    -0.81
     Shakspeare
    -0.80
     Anſ
    -0.78
     Cæsar
    -0.77
    POSITIVE LOGITS
     so
    0.67
     thus
    0.60
    因此
    0.57
    esez
    0.57
    editForm
    0.56
     Thus
    0.56
     therefore
    0.55
     hence
    0.55
     So
    0.55
     somit
    0.54
    Act Density 0.291%

    No Known Activations