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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mathrm
    -0.51
    だい
    -0.46
    Тер
    -0.45
     T
    -0.43
    middle
    -0.42
     
    -0.41
    胆
    -0.40
    激
    -0.40
    Middle
    -0.40
    1
    -0.40
    POSITIVE LOGITS
     '\\;'
    1.01
    IntoConstraints
    0.97
    <bos>
    0.94
     Савезне
    0.92
    antMatchers
    0.91
     useAppContext
    0.86
     InputDecoration
    0.83
     StringTokenizer
    0.82
     ainfi
    0.81
    yntaxException
    0.81
    Act Density 0.457%

    No Known Activations