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

    Neuronpedia

    INDEX
    Explanations

    terms related to warranties and fitness for a particular purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     –
    -0.54
     flip
    -0.51
    </strong>
    -0.48
    hoga
    -0.47
    hup
    -0.47
    fo
    -0.46
    io
    -0.46
     (
    -0.46
     Change
    -0.46
    Story
    -0.45
    POSITIVE LOGITS
     purpoſe
    0.83
     itſelf
    0.82
     uſe
    0.79
     perſon
    0.79
     iſt
    0.77
     pleaſure
    0.76
    ſelf
    0.75
     Majefty
    0.75
    DebuggerNonUser
    0.74
     himſelf
    0.73
    Act Density 0.042%

    No Known Activations