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

    Neuronpedia

    INDEX
    Explanations

    actions and interactions involving physical touch

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that indicate movement or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irin
    -0.72
    tain
    -0.70
     Kardash
    -0.68
     predecessors
    -0.65
    ãĥİ
    -0.64
     circus
    -0.63
     weddings
    -0.62
    obyl
    -0.61
    entin
    -0.61
    cedented
    -0.61
    POSITIVE LOGITS
     angrily
    0.82
     hurried
    0.77
     reluctantly
    0.75
     nervously
    0.73
     promptly
    0.70
    anke
    0.69
     calmly
    0.68
     immediately
    0.68
    Option
    0.68
    ographs
    0.67
    Act Density 0.431%

    No Known Activations