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

    mentions of relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Args
    -0.69
    moon
    -0.69
    asus
    -0.66
    Synopsis
    -0.65
    Naz
    -0.63
    fare
    -0.63
    PDATE
    -0.62
     NX
    -0.62
    \\\\\\\\\\\\\\\\
    -0.62
    hawks
    -0.61
    POSITIVE LOGITS
    hips
    1.37
    ystem
    1.19
    ensical
    1.14
    poons
    1.10
    hip
    1.03
    ettings
    1.02
    omething
    1.01
    pring
    0.98
    ourcing
    0.96
    mith
    0.94
    Act Density 0.098%

    No Known Activations