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

    Neuronpedia

    INDEX
    Explanations

    references to the user or direct address to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.62
    TagMode
    -0.46
    GOTREF
    -0.45
    UrlResolution
    -0.43
     пусть
    -0.42
    AndEndTag
    -0.42
    esez
    -0.41
    AddTagHelper
    -0.40
     soit
    -0.40
     decir
    -0.40
    POSITIVE LOGITS
     plan
    0.68
     wish
    0.68
     prefer
    0.68
     suspect
    0.67
     decide
    0.66
     happen
    0.57
     intend
    0.56
     like
    0.52
     require
    0.51
    enumi
    0.50
    Act Density 0.200%

    No Known Activations