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

    Neuronpedia

    INDEX
    Explanations

    terms related to dual systems or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Huss
    -0.90
     calendriers
    -0.90
     puc
    -0.85
     McGovern
    -0.83
    Tir
    -0.83
     tir
    -0.82
     ?>">
    -0.81
     Pugh
    -0.79
    ity
    -0.78
    omencl
    -0.77
    POSITIVE LOGITS
    ñores
    0.84
     myſelf
    0.82
     Dual
    0.82
    Dual
    0.81
    czerw
    0.79
     DUAL
    0.78
    ALTH
    0.77
     itſelf
    0.77
    rzez
    0.77
    evsky
    0.76
    Act Density 0.152%

    No Known Activations