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

    Neuronpedia

    INDEX
    Explanations

    advanced techniques or strategies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to strategies and solutions for community safety and innovative problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brotherhood
    -0.71
    OUS
    -0.67
    OV
    -0.64
     Carnage
    -0.64
    athan
    -0.63
    onel
    -0.62
     IDF
    -0.62
    Else
    -0.60
    Spoiler
    -0.58
    rip
    -0.57
    POSITIVE LOGITS
    poons
    1.17
    uggest
    1.13
    mith
    1.09
    hops
    1.06
    paces
    1.05
    etter
    1.04
    hooting
    1.04
    etting
    1.00
    hips
    1.00
    uits
    1.00
    Act Density 0.143%

    No Known Activations