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

    Neuronpedia

    INDEX
    Explanations

    terms related to confirmation and diagnostic imaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UserScript
    -0.61
     venait
    -0.61
     protoimpl
    -0.59
    Anlage
    -0.59
     heiress
    -0.58
     rowspan
    -0.56
     Hame
    -0.56
     للاسماء
    -0.55
    ialog
    -0.55
    aterin
    -0.55
    POSITIVE LOGITS
    confirm
    0.89
    Confirm
    0.88
     Confirm
    0.85
     decline
    0.81
     confirm
    0.81
     dense
    0.77
     confirmation
    0.74
     Decline
    0.74
    Confirmation
    0.73
     Confirmation
    0.70
    Act Density 0.141%

    No Known Activations