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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpersonal relationships

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional connections and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    corn
    -0.73
    ighed
    -0.70
    oker
    -0.69
    crow
    -0.68
    Naz
    -0.67
    ////////////////////////////////
    -0.66
    rpm
    -0.65
     Noon
    -0.65
    inently
    -0.65
    LV
    -0.64
    POSITIVE LOGITS
     between
    1.11
    hips
    1.03
     forged
    0.86
    between
    0.83
     Between
    0.82
     dynamics
    0.80
     builder
    0.79
     relationships
    0.79
     bloss
    0.78
     with
    0.78
    Act Density 0.064%

    No Known Activations