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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical specifications and procedural guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by prepositions or "that"

    np_acts-logits-general · gemini-2.0-flash

    abstract concepts and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.19
     myſelf
    -1.14
    IntoConstraints
    -1.09
     pleaſure
    -1.08
    ſelves
    -1.06
     greateſt
    -1.06
     ſeveral
    -1.02
     Majefty
    -1.01
     poffible
    -1.00
     purpoſe
    -0.99
    POSITIVE LOGITS
     of
    0.76
     in
    0.59
     for
    0.59
    /
    0.59
     list
    0.58
    <eos>
    0.55
    ,
    0.52
     to
    0.51
    list
    0.50
     $\
    0.49
    Act Density 1.396%

    No Known Activations