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

    Neuronpedia

    INDEX
    Explanations

    phrases related to chemical substances and political topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Curve
    -0.81
     Brooks
    -0.76
     Taste
    -0.70
     Grind
    -0.68
     Grill
    -0.66
     Orchestra
    -0.66
     throats
    -0.65
     Heights
    -0.64
     Spoon
    -0.64
    oice
    -0.64
    POSITIVE LOGITS
    linear
    1.26
    occup
    1.19
    human
    1.19
    atomic
    1.15
    competitive
    1.14
    urban
    1.14
    clinical
    1.12
    commun
    1.12
    jud
    1.11
    continental
    1.11
    Act Density 3.393%

    No Known Activations