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

    Neuronpedia

    INDEX
    Explanations

    phrases related to requests for information concerning incidents or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erture
    -0.15
     Suff
    -0.14
    íĿ¥
    -0.14
    otron
    -0.14
    ogle
    -0.14
    isman
    -0.14
     Protest
    -0.14
    .AspNet
    -0.14
    _CURSOR
    -0.13
    unan
    -0.13
    POSITIVE LOGITS
     anonymously
    0.27
     anonymous
    0.25
     Crime
    0.25
    Crime
    0.24
     confidential
    0.24
     anonymity
    0.22
    anonymous
    0.22
     anon
    0.21
    Anonymous
    0.21
     anyone
    0.20
    Act Density 0.012%

    No Known Activations