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

    Neuronpedia

    INDEX
    Explanations

    phrases related to password and account security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pie
    -0.16
    thal
    -0.15
    iske
    -0.15
    jack
    -0.15
    NST
    -0.14
    place
    -0.14
     Enlight
    -0.14
    è²
    -0.13
    Jar
    -0.13
    bourg
    -0.13
    POSITIVE LOGITS
     forgotten
    0.25
     reset
    0.24
     Forgotten
    0.23
     Reset
    0.22
     forgot
    0.21
    Reset
    0.21
     resets
    0.21
    Forgot
    0.21
    .reset
    0.20
     recovery
    0.20
    Act Density 0.022%

    No Known Activations