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

    Neuronpedia

    INDEX
    Explanations

    references to physical contact and tactile experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.84
     stället
    -0.77
     religieuse
    -0.76
     scolas
    -0.76
     Aryan
    -0.75
     owls
    -0.74
     humains
    -0.73
     Schülern
    -0.71
     chrétienne
    -0.71
     Milner
    -0.71
    POSITIVE LOGITS
     TOUCH
    2.02
     Touch
    1.95
     touch
    1.93
    TOUCH
    1.92
    touch
    1.77
    Touch
    1.74
     touches
    1.61
     touching
    1.54
    touched
    1.48
    Touches
    1.46
    Act Density 0.045%

    No Known Activations