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

    Neuronpedia

    INDEX
    Explanations

    the phrase "that" and its variations used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùĩ
    -0.20
    ãģĤãĤĭ
    -0.20
    amp
    -0.19
    (
    -0.18
    us
    -0.17
    ãģĤãĤĬ
    -0.17
    ãģĤãģ£ãģŁ
    -0.17
    ity
    -0.15
    ive
    -0.15
    idon
    -0.15
    POSITIVE LOGITS
    ched
    0.29
     alone
    0.25
     same
    0.24
    ching
    0.24
    'll
    0.21
    -ÑĤо
    0.21
    alone
    0.20
    cher
    0.20
    ’ll
    0.20
     же
    0.19
    Act Density 0.084%

    No Known Activations