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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the influence of drugs or alcohol

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.80
    UAL
    -0.74
    \\\\\\\\
    -0.71
    hare
    -0.69
    BOOK
    -0.66
     QC
    -0.66
    OPLE
    -0.66
    manship
    -0.65
    eers
    -0.64
     Sapphire
    -0.64
    POSITIVE LOGITS
    inite
    1.29
    rastructure
    1.27
    luence
    1.26
    licted
    1.15
    ractions
    1.12
    inity
    1.12
    amous
    1.05
    ertility
    1.04
    urred
    1.04
    raction
    1.03
    Act Density 0.005%

    No Known Activations