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

    Neuronpedia

    INDEX
    Explanations

    the word "single" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sing
    -0.18
    ãģĬãĤĬ
    -0.16
    ses
    -0.16
    etten
    -0.15
    soever
    -0.15
     entire
    -0.14
    semblies
    -0.14
    ppers
    -0.14
     Few
    -0.14
     same
    -0.14
    POSITIVE LOGITS
    tons
    0.45
     solitary
    0.27
    /single
    0.26
    -minded
    0.26
    -digit
    0.25
    -handed
    0.23
    -purpose
    0.22
    ChildScrollView
    0.21
    /group
    0.21
    -sided
    0.21
    Act Density 0.022%

    No Known Activations