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

    Neuronpedia

    INDEX
    Explanations

    mentions of razor-related objects or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to razors and shaving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.88
     Miranda
    -0.76
    phis
    -0.70
    κ
    -0.69
    oyer
    -0.69
    ichick
    -0.68
    estine
    -0.67
     quo
    -0.65
    ãĤ±
    -0.65
    estation
    -0.63
    POSITIVE LOGITS
    brush
    0.94
    utical
    0.94
     blades
    0.92
    stal
    0.91
     shaving
    0.91
    utic
    0.91
     shave
    0.89
     cartridges
    0.86
    utics
    0.86
    cliffe
    0.81
    Act Density 0.019%

    No Known Activations