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

    Neuronpedia

    INDEX
    Explanations

    verbs and their associated actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orian
    -0.17
    418
    -0.15
    irie
    -0.15
     Aqu
    -0.15
    nan
    -0.15
    icari
    -0.15
    Aqu
    -0.14
    ctr
    -0.14
    zan
    -0.14
    å·Ŀ
    -0.14
    POSITIVE LOGITS
    rada
    0.21
     rad
    0.20
    RAD
    0.18
    ãĤ¯ãĥŃ
    0.18
    rad
    0.16
     Rad
    0.16
     Robbins
    0.16
    radi
    0.16
     RAD
    0.15
     dro
    0.15
    Act Density 0.027%

    No Known Activations