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

    Neuronpedia

    INDEX
    Explanations

    phrases about perception and security in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orf
    -0.15
    xFFF
    -0.15
    aille
    -0.15
     Pearce
    -0.14
    inus
    -0.14
    ghi
    -0.14
     Serge
    -0.14
    isque
    -0.14
     Ramirez
    -0.14
     Foreign
    -0.13
    POSITIVE LOGITS
    sink
    0.17
     Cousins
    0.14
    ses
    0.14
     basically
    0.14
    .sock
    0.13
     sink
    0.13
    icum
    0.13
    ì¶ĺ
    0.13
    olin
    0.13
     essentially
    0.13
    Act Density 0.138%

    No Known Activations