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

    Neuronpedia

    INDEX
    Explanations

    references to physical touch and contact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vacy
    -0.41
     ennemis
    -0.38
     дописавши
    -0.37
    醐
    -0.37
     Sahne
    -0.36
     Daarom
    -0.36
    anlagen
    -0.35
     Deshalb
    -0.34
     boste
    -0.34
     vyp
    -0.34
    POSITIVE LOGITS
     touch
    2.11
    touch
    2.03
     Touch
    2.02
     TOUCH
    1.99
    Touch
    1.89
     touches
    1.80
    TOUCH
    1.79
     touched
    1.72
     touching
    1.69
    touches
    1.57
    Act Density 0.093%

    No Known Activations