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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a summary or conclusion in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.69
    principalColumn
    -0.53
    OuterAlt
    -0.51
    ⏟
    -0.49
     Lul
    -0.48
    exitRule
    -0.48
    AISSEE
    -0.48
     ujednoznacz
    -0.48
     domo
    -0.48
    batik
    -0.48
    POSITIVE LOGITS
     inoltre
    0.74
     lisäksi
    0.71
    Inoltre
    0.71
     furthermore
    0.70
     Inoltre
    0.69
    Furthermore
    0.69
     navíc
    0.65
     además
    0.65
     Furthermore
    0.63
     dessutom
    0.63
    Act Density 0.461%

    No Known Activations