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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "touch" and its variations in context to interactions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.86
     scolas
    -0.81
     stället
    -0.80
     ennemis
    -0.77
     religieuse
    -0.76
     Aryan
    -0.75
     owls
    -0.74
     Schülern
    -0.73
     chrétienne
    -0.71
     humains
    -0.71
    POSITIVE LOGITS
     TOUCH
    2.15
     touch
    2.08
     Touch
    2.07
    TOUCH
    2.02
    touch
    1.89
    Touch
    1.84
     touches
    1.74
     touching
    1.65
     touched
    1.58
    touched
    1.57
    Act Density 0.060%

    No Known Activations