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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spatial movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quin
    -0.15
    elle
    -0.15
    cel
    -0.14
     metabol
    -0.14
    Elite
    -0.14
    amon
    -0.14
    elite
    -0.13
    ÑĸÑĶ
    -0.13
    nt
    -0.13
    table
    -0.13
    POSITIVE LOGITS
    resher
    0.16
    ianne
    0.16
     åł
    0.15
    iti
    0.15
    ewise
    0.15
    aggi
    0.15
    licos
    0.14
    ordion
    0.14
     Zi
    0.14
    esinde
    0.14
    Act Density 0.074%

    No Known Activations