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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication or interaction

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "getting in" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coron
    -0.70
     bene
    -0.68
     sacrific
    -0.57
    Percent
    -0.57
     unle
    -0.56
     testament
    -0.54
    cia
    -0.54
    HCR
    -0.54
     indicating
    -0.53
     Pompe
    -0.53
    POSITIVE LOGITS
     touch
    1.28
     trouble
    1.24
    ked
    0.99
    touch
    0.95
     Touch
    0.93
    Touch
    0.89
     contact
    0.89
     Trouble
    0.87
     shape
    0.87
     bed
    0.83
    Act Density 0.058%

    No Known Activations