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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives related to affection or care

    oai_token-act-pair · gpt-3.5-turbo

    expressions of love and caring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.96
    culosis
    -0.85
    inates
    -0.80
    oggles
    -0.80
    obyl
    -0.79
    acular
    -0.73
    idation
    -0.72
    arily
    -0.71
    aries
    -0.71
    ulence
    -0.70
    POSITIVE LOGITS
     minded
    0.79
    glers
    0.72
     adoptive
    0.71
     embrace
    0.71
    tons
    0.67
     supportive
    0.67
     entreprene
    0.67
     disposition
    0.66
     Wife
    0.65
     energies
    0.64
    Act Density 0.046%

    No Known Activations