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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to honorary titles or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to emergencies and urgent situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ogre
    -0.74
     cooker
    -0.68
     Strauss
    -0.66
    bill
    -0.63
     Pilgrim
    -0.63
     burgers
    -0.62
     guiActiveUnfocused
    -0.60
     underest
    -0.60
     Yoga
    -0.59
    wana
    -0.59
    POSITIVE LOGITS
    gency
    1.08
    itus
    1.01
    gent
    1.01
    andum
    0.99
    oing
    0.92
    acy
    0.92
     emer
    0.91
    oint
    0.89
    ira
    0.88
    itable
    0.87
    Act Density 0.014%

    No Known Activations