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

    Neuronpedia

    INDEX
    Explanations

    words related to detection, particularly verbs indicating the action of discovering or identifying something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of detection and identifying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mort
    -0.94
    emate
    -0.76
    nesia
    -0.73
    egal
    -0.72
    erer
    -0.71
    ember
    -0.70
    ovie
    -0.70
    adra
    -0.68
    itent
    -0.67
    ammy
    -0.67
    POSITIVE LOGITS
     flaws
    0.85
    ively
    0.81
     faults
    0.77
     detection
    0.72
     Detection
    0.72
     detect
    0.70
    ibly
    0.69
    ible
    0.68
     leakage
    0.68
     weaknesses
    0.67
    Act Density 0.042%

    No Known Activations