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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hormones and medical conditions affected by hormonal imbalances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    varlak
    -0.53
     signore
    -0.52
     confé
    -0.52
     chitar
    -0.51
     PLW
    -0.50
     silenzio
    -0.49
     kuah
    -0.49
     fanci
    -0.49
     Valentín
    -0.48
     signor
    -0.48
    POSITIVE LOGITS
     hormones
    1.13
     hormone
    1.13
     hormonal
    0.95
    Horm
    0.85
     hormon
    0.82
    horm
    0.81
     Hormone
    0.80
     Hormones
    0.78
     horm
    0.77
     Horm
    0.67
    Act Density 0.086%

    No Known Activations