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

    Neuronpedia

    INDEX
    Explanations

    phrases analyzing perspectives or views on specific issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.54
     Ste
    -0.49
     تانيه
    -0.48
    ’
    -0.47
     or
    -0.44
    dai
    -0.44
     Che
    -0.44
    das
    -0.44
    /
    -0.43
     and
    -0.42
    POSITIVE LOGITS
     diſt
    0.75
     ſal
    0.75
     feroit
    0.74
     ſtate
    0.73
     uſ
    0.72
     nmax
    0.72
     ſur
    0.71
     ſtand
    0.70
     ſtill
    0.70
     eſſ
    0.69
    Act Density 0.257%

    No Known Activations