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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and encryption

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to internet privacy and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itars
    -1.17
    mingham
    -0.78
     Cu
    -0.74
     Pyro
    -0.72
    elf
    -0.70
    ¥µ
    -0.68
    rote
    -0.68
    alli
    -0.66
    ports
    -0.66
    umar
    -0.65
    POSITIVE LOGITS
     informants
    0.69
    ²¾
    0.68
     compliant
    0.63
     Advantage
    0.62
     Secure
    0.61
    åħ
    0.58
     Linear
    0.58
    LAB
    0.58
     neurot
    0.57
     candidacy
    0.57
    Act Density 0.221%

    No Known Activations