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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mental health and support systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "")
    -0.79
    `,
    -0.79
    anadium
    -0.76
     Malte
    -0.75
    prüche
    -0.72
    ostante
    -0.71
     Hv
    -0.71
    scrapy
    -0.71
    LookAnd
    -0.71
    '));
    -0.69
    POSITIVE LOGITS
     Hills
    0.70
    czy
    0.69
     Brag
    0.68
     ActionBar
    0.65
    tahan
    0.64
     Thessalon
    0.64
     bras
    0.63
     Lawton
    0.63
     Ayers
    0.63
     Hutt
    0.62
    Act Density 0.855%

    No Known Activations