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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging readers to engage or comment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ercise
    -0.15
    rego
    -0.15
    vang
    -0.15
    apus
    -0.15
    ácil
    -0.14
    ãĥĥãĥĪ
    -0.14
    reek
    -0.14
    reck
    -0.14
    scopy
    -0.14
    lene
    -0.14
    POSITIVE LOGITS
    alone
    0.26
     behind
    0.24
     comment
    0.23
     Behind
    0.22
     alone
    0.22
     comments
    0.21
     Comment
    0.21
    beh
    0.21
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    0.20
    CriticalSection
    0.20
    Act Density 0.010%

    No Known Activations