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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atura
    -0.17
    WithMany
    -0.16
     more
    -0.15
    ahlen
    -0.14
     nid
    -0.14
    plr
    -0.14
    gers
    -0.14
     least
    -0.14
    aturas
    -0.14
    ÑĨÑĸйна
    -0.14
    POSITIVE LOGITS
    åĮħæĭ¬
    0.15
    548
    0.14
     ê²ĥëıĦ
    0.14
    akin
    0.14
    opot
    0.14
    Means
    0.13
    759
    0.13
    ince
    0.13
    .us
    0.12
     #:
    0.12
    Act Density 0.060%

    No Known Activations