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

    Neuronpedia

    INDEX
    Explanations

    words related to security and defense

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to security and defense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erent
    -0.82
    iasco
    -0.74
    Cola
    -0.73
    ãĤ¨ãĥ«
    -0.69
    姫
    -0.69
    undred
    -0.68
    ombo
    -0.67
    ritch
    -0.67
     sugg
    -0.64
    æµ
    -0.64
    POSITIVE LOGITS
    warts
    0.83
    ascript
    0.64
     passwords
    0.64
     wearer
    0.64
     Compensation
    0.64
    illance
    0.64
     takedown
    0.62
     perimeter
    0.62
     indicators
    0.61
    metics
    0.61
    Act Density 0.248%

    No Known Activations