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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "from."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramer
    -0.17
    istol
    -0.15
    AIT
    -0.15
    terms
    -0.15
    ãģ°
    -0.14
    lah
    -0.14
    lew
    -0.13
    organisms
    -0.13
    移åĪ°
    -0.13
     thêm
    -0.13
    POSITIVE LOGITS
    /to
    0.27
    /by
    0.20
     scratch
    0.18
    /about
    0.17
    scratch
    0.15
     Byrne
    0.15
    än
    0.14
    _logits
    0.14
    alim
    0.14
    alto
    0.14
    Act Density 0.310%

    No Known Activations