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

    Neuronpedia

    INDEX
    Explanations

    expressions of reluctance or unwillingness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.08
     pleaſure
    -1.07
     purpoſe
    -1.05
     Efq
    -1.02
     ſta
    -1.01
     myſelf
    -1.01
     houſe
    -1.00
     poffe
    -0.96
     ſtate
    -0.94
     Jefus
    -0.94
    POSITIVE LOGITS
     ever
    0.60
     or
    0.57
    /
    0.55
     risk
    0.54
     yet
    0.52
     me
    0.52
    ,
    0.50
     non
    0.49
     any
    0.49
     re
    0.49
    Act Density 0.267%

    No Known Activations