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

    Neuronpedia

    INDEX
    Explanations

    terms related to peace and its quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viſ
    -0.74
     pleaſure
    -0.74
     ſte
    -0.71
     itſelf
    -0.69
     houſe
    -0.68
     faſt
    -0.65
     ſta
    -0.65
    ſelf
    -0.63
     juſ
    -0.61
     ſmall
    -0.59
    POSITIVE LOGITS
    Decent
    0.49
     laaj
    0.48
    ParallelGroup
    0.48
     decent
    0.47
     Decent
    0.47
    IBOutlet
    0.46
     feedback
    0.46
    guien
    0.44
    zeich
    0.43
     muun
    0.43
    Act Density 0.285%

    No Known Activations