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

    Neuronpedia

    INDEX
    Explanations

    phrases related to falling in love

    oai_token-act-pair · gpt-3.5-turbo

    expressions of love or affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illin
    -0.79
    authorized
    -0.74
    sk
    -0.74
    opers
    -0.69
    uckles
    -0.67
    nesota
    -0.65
    vernment
    -0.63
     qualifiers
    -0.63
     fielded
    -0.62
    grim
    -0.62
    POSITIVE LOGITS
    Film
    0.76
     uncond
    0.73
    amorph
    0.73
    enment
    0.71
    thood
    0.70
    antically
    0.68
    Lens
    0.67
    wine
    0.67
    ļéĨĴ
    0.67
    isons
    0.66
    Act Density 0.029%

    No Known Activations