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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discovering or uncovering information

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the act of discovering or learning new information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.79
    interstitial
    -0.77
    orously
    -0.73
    avorite
    -0.71
    export
    -0.70
    iets
    -0.69
    oil
    -0.68
    cious
    -0.68
    oulder
    -0.68
    Textures
    -0.68
    POSITIVE LOGITS
    yer
    0.82
    posts
    0.77
     è£ıè
    0.75
     how
    0.75
    stadt
    0.74
    wards
    0.73
    casts
    0.67
     loopholes
    0.66
    ropolis
    0.64
     sexism
    0.64
    Act Density 0.035%

    No Known Activations