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

    Neuronpedia

    INDEX
    Explanations

    attends to certain special tokens related to their appearances in strings or language structures from any subsequent tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.15
    1:0.10
    2:0.28
    3:0.09
    4:0.10
    5:0.13
    6:0.05
    7:0.07
    Negative Logits
    expandindo
    -0.45
    хьтан
    -0.37
    ьаж
    -0.36
    цездатний
    -0.34
    IndentedString
    -0.33
     jsPsych
    -0.33
     ModelExpression
    -0.32
    GEBURTSDATUM
    -0.31
     nonatomic
    -0.30
     snippetHide
    -0.30
    POSITIVE LOGITS
     مشين
    0.27
     plomb
    0.26
    .*")]
    0.26
    احث
    0.26
    ShouldBe
    0.26
    ChromeDriver
    0.26
    inim
    0.25
    HashCode
    0.25
    Parcelable
    0.25
     ci
    0.25
    Act Density 0.001%

    No Known Activations