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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related expressions emphasizing frequency and occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereby
    -0.16
    frag
    -0.15
    rupt
    -0.14
     whats
    -0.13
    ucz
    -0.13
     Morrow
    -0.13
    WN
    -0.13
    é¡ĺ
    -0.13
    _ATTACH
    -0.13
    amines
    -0.13
    POSITIVE LOGITS
     where
    0.53
    where
    0.42
     ÏĮÏĢοÏħ
    0.39
     où
    0.39
     donde
    0.37
    	where
    0.36
     Where
    0.33
     waar
    0.33
    _where
    0.33
     где
    0.32
    Act Density 0.140%

    No Known Activations