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

    Neuronpedia

    INDEX
    Explanations

    the presence and frequency of conjunctions and other connecting phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĻ
    -0.16
    atica
    -0.15
    umba
    -0.15
    ghi
    -0.15
    ute
    -0.15
    UTE
    -0.14
    ppy
    -0.14
    exampleInputEmail
    -0.14
    иÑģÑĤÑĢа
    -0.14
    ãĥ³ãĥĦ
    -0.13
    POSITIVE LOGITS
     however
    0.18
     according
    0.17
    rats
    0.15
     إذ
    0.14
    .sam
    0.14
     HOLDERS
    0.14
     Ple
    0.14
     же
    0.14
     herr
    0.14
     According
    0.14
    Act Density 0.083%

    No Known Activations