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

    Neuronpedia

    INDEX
    Explanations

    words related to growth or development

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ro" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Object
    -0.64
     Crit
    -0.60
     EntityItem
    -0.60
     Rouge
    -0.58
     Mens
    -0.57
     misunderstand
    -0.57
     labels
    -0.56
     demands
    -0.56
     Norn
    -0.56
     Hawks
    -0.54
    POSITIVE LOGITS
    ving
    1.23
    oster
    1.11
    tted
    1.10
    aches
    1.03
    dding
    1.03
    cks
    1.02
    vers
    0.97
    oting
    0.95
    aming
    0.95
    verbs
    0.94
    Act Density 0.018%

    No Known Activations