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

    Neuronpedia

    INDEX
    Explanations

    phrases related to increasing or progressing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to increasing trends or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anders
    -0.81
    ADS
    -0.72
    adr
    -0.68
    astical
    -0.68
    aimon
    -0.67
    APH
    -0.65
    andering
    -0.64
    astically
    -0.62
    pez
    -0.62
    gur
    -0.62
    POSITIVE LOGITS
    ly
    2.62
    LY
    1.63
    liness
    1.40
    lies
    1.32
    lys
    1.28
    ity
    1.08
    edly
    1.06
    fully
    1.06
    ELY
    1.04
    liest
    1.02
    Act Density 0.101%

    No Known Activations