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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of staying or remaining in a particular state or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.18
    vale
    -0.17
    antine
    -0.16
    äº
    -0.16
    erm
    -0.15
    nap
    -0.15
    ured
    -0.15
    rypted
    -0.14
    mente
    -0.14
    esc
    -0.14
    POSITIVE LOGITS
    cation
    0.23
    ders
    0.19
     away
    0.18
     true
    0.18
    true
    0.17
     tuned
    0.16
    alive
    0.16
    -away
    0.16
     подалÑĮ
    0.16
    _alive
    0.15
    Act Density 0.030%

    No Known Activations