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

    Neuronpedia

    INDEX
    Explanations

    references to thresholds in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.04
     Efq
    -1.04
     Monfieur
    -1.02
     ſever
    -1.01
     ſtate
    -1.01
     purpoſe
    -1.00
     myſelf
    -0.99
     Jefus
    -0.98
     pleaſure
    -0.98
     Diſ
    -0.98
    POSITIVE LOGITS
     A
    0.75
     no
    0.73
     se
    0.72
     X
    0.71
     brief
    0.69
     
    0.69
     L
    0.69
     Se
    0.68
     n
    0.66
     V
    0.66
    Act Density 0.161%

    No Known Activations