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

    Neuronpedia

    INDEX
    Explanations

    terms related to anchoring or stability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تا
    -0.16
    enk
    -0.15
    enger
    -0.14
    ियर
    -0.14
    ục
    -0.14
    REATED
    -0.14
    aç
    -0.14
    ToEnd
    -0.14
    earing
    -0.14
    andro
    -0.14
    POSITIVE LOGITS
    avn
    0.15
    OCK
    0.15
    ighb
    0.15
    /GPL
    0.15
    мÑĥ
    0.14
    stri
    0.14
     goof
    0.14
    à¥įध
    0.14
    룬
    0.14
    aser
    0.13
    Act Density 0.011%

    No Known Activations