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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating thoughts or opinions expressed in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     emperador
    -0.35
     setengah
    -0.33
     estimé
    -0.32
     Superhost
    -0.31
     towarzys
    -0.31
    DataSetChanged
    -0.31
    žiu
    -0.31
     Catawiki
    -0.30
     Ebenso
    -0.30
     infierno
    -0.30
    POSITIVE LOGITS
     Pingback
    0.75
     ujednoznacz
    0.65
    LikeLiked
    0.65
    Ping
    0.62
    LikeLike
    0.59
    rungsseite
    0.57
     @"/
    0.57
    […]
    0.57
     Ping
    0.54
    ConstraintMaker
    0.54
    Act Density 0.182%

    No Known Activations