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

    Neuronpedia

    INDEX
    Explanations

    words related to the act of hiding or concealing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĺi
    -0.15
    opup
    -0.15
    orous
    -0.15
    LAR
    -0.15
    ADF
    -0.15
    emann
    -0.15
    agic
    -0.14
    ungi
    -0.14
     ÙĪات
    -0.14
    oodle
    -0.14
    POSITIVE LOGITS
    pcion
    0.32
    aling
    0.29
    iv
    0.29
    ives
    0.27
    ivers
    0.27
    pción
    0.26
    iving
    0.26
    voir
    0.26
    ptr
    0.25
    aler
    0.25
    Act Density 0.008%

    No Known Activations