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

    Neuronpedia

    INDEX
    Explanations

    references to parent companies or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "parent" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atility
    -0.91
    okers
    -0.73
    anwhile
    -0.71
     Flavoring
    -0.70
     Antar
    -0.69
    odies
    -0.69
    schild
    -0.68
     Medal
    -0.68
    paio
    -0.67
     Hawks
    -0.67
    POSITIVE LOGITS
    hetical
    1.53
    hesis
    1.42
    hetically
    1.18
    heses
    1.15
    parents
    0.97
    hood
    0.86
    parent
    0.80
     parent
    0.80
    Parents
    0.80
    Parent
    0.78
    Act Density 0.016%

    No Known Activations