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

    Neuronpedia

    INDEX
    Explanations

    references to falsehoods or misleading representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icast
    -0.17
    ulton
    -0.17
    iselect
    -0.14
    rank
    -0.14
    .scalablytyped
    -0.14
    ahy
    -0.13
    üb
    -0.13
    ikk
    -0.13
    laz
    -0.13
    rl
    -0.13
    POSITIVE LOGITS
    hood
    0.33
     positives
    0.26
    -flag
    0.26
     alarms
    0.26
     pret
    0.25
     alarm
    0.23
    /false
    0.23
    -positive
    0.23
    flag
    0.21
    pret
    0.21
    Act Density 0.037%

    No Known Activations