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

    Neuronpedia

    INDEX
    Explanations

    words related to freedom, openness, and accessibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to freedom and openness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.73
    vae
    -0.71
    »Ĵ
    -0.70
     Huss
    -0.69
     vis
    -0.68
     Miko
    -0.66
     proble
    -0.65
    Timeout
    -0.62
    MpServer
    -0.62
    nox
    -0.61
    POSITIVE LOGITS
     roam
    0.82
     unrestricted
    0.81
     unlimited
    0.77
    open
    0.73
    Initialized
    0.70
     open
    0.68
    plugins
    0.67
     slaves
    0.67
     Libre
    0.67
    ercise
    0.66
    Act Density 0.073%

    No Known Activations