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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "inwardness" or things inside something

    oai_token-act-pair · gpt-3.5-turbo

    references to innuendos and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marijuana
    -0.77
    ################################
    -0.75
     Ryder
    -0.73
    ————————————————
    -0.68
    911
    -0.66
     Species
    -0.66
    Winged
    -0.65
     Forces
    -0.64
    UNCH
    -0.64
     Flavoring
    -0.62
    POSITIVE LOGITS
     inn
    1.11
    cloth
    0.97
     neighb
    0.89
    ship
    0.82
     tremend
    0.82
    urst
    0.81
    ships
    0.79
     traged
    0.77
     oun
    0.76
    ately
    0.75
    Act Density 0.010%

    No Known Activations