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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreements or authorized actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LU
    -0.16
    ôi
    -0.14
     ÑĪÑĤÑĥ
    -0.13
    ermen
    -0.13
    plevel
    -0.13
    ãĢĩ
    -0.13
     projektu
    -0.13
    zcze
    -0.13
    Loop
    -0.13
     quite
    -0.13
    POSITIVE LOGITS
     la
    0.72
     les
    0.50
     las
    0.48
     los
    0.44
    la
    0.43
    _la
    0.40
    -la
    0.40
     le
    0.38
     La
    0.37
     el
    0.36
    Act Density 0.136%

    No Known Activations