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

    Neuronpedia

    INDEX
    Explanations

    pronouns and determiners followed by verbs expressing interaction or association with specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to relationships and connections with people or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    puter
    -0.68
    trap
    -0.67
    pez
    -0.63
    artifacts
    -0.62
    PIN
    -0.60
     Patt
    -0.59
    adobe
    -0.59
    stage
    -0.57
     Tracker
    -0.57
    äºĶ
    -0.57
    POSITIVE LOGITS
    soever
    0.88
    usalem
    0.75
    omes
    0.64
    illas
    0.63
    atar
    0.63
    xual
    0.62
    omever
    0.62
    many
    0.62
    sey
    0.62
    igor
    0.60
    Act Density 0.031%

    No Known Activations