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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     atleast
    -0.17
     både
    -0.16
     Nearly
    -0.16
    èĩ³å°ij
    -0.16
    åĩłä¹İ
    -0.15
     actionTypes
    -0.15
     BOTH
    -0.14
    Nearly
    -0.14
    REATED
    -0.14
     поÑĩÑĤи
    -0.14
    POSITIVE LOGITS
     partial
    0.20
     a
    0.19
     token
    0.18
     enough
    0.18
     moderate
    0.17
     minor
    0.17
     one
    0.17
     modest
    0.17
     limited
    0.17
    ifiable
    0.16
    Act Density 0.083%

    No Known Activations