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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĤãĤĭ
    -0.23
     and
    -0.23
    ãģĤãĤĬ
    -0.19
    ãģĤãģ£ãģŁ
    -0.17
    (
    -0.17
     thereof
    -0.15
    sic
    -0.15
     adalah
    -0.15
     or
    -0.15
    (and
    -0.14
    POSITIVE LOGITS
    ched
    0.31
    'll
    0.28
    ching
    0.27
    ’ll
    0.26
     nobody
    0.24
    's
    0.24
    ’s
    0.23
     everyone
    0.23
    ch
    0.21
    'd
    0.20
    Act Density 0.258%

    No Known Activations