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

    Neuronpedia

    INDEX
    Explanations

    phrases related to completing tasks or achieving goals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enjoyment or appreciation of experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .''
    -0.79
    ]."
    -0.78
    ."[
    -0.78
     thereto
    -0.77
    )."
    -0.75
    ).[
    -0.74
    .''.
    -0.73
    ''.
    -0.72
     thereby
    -0.71
    ."
    -0.68
    POSITIVE LOGITS
     FANTASY
    0.84
     Patreon
    0.75
     spoilers
    0.72
     Spoiler
    0.69
     Tags
    0.67
     spoiler
    0.67
     Nerd
    0.67
     disclaimer
    0.66
     nutshell
    0.66
    reenshots
    0.64
    Act Density 2.469%

    No Known Activations