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

    Neuronpedia

    INDEX
    Explanations

    the word "one" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸ĺ
    -0.16
    Occurred
    -0.15
    rogram
    -0.15
    rente
    -0.15
     киÑĪ
    -0.14
    agli
    -0.14
    inois
    -0.14
    laz
    -0.14
    igel
    -0.13
    lant
    -0.13
    POSITIVE LOGITS
     else
    0.34
     ever
    0.28
     except
    0.25
    except
    0.24
    else
    0.23
    	else
    0.23
     EVER
    0.23
    ever
    0.21
     ELSE
    0.20
    -ever
    0.20
    Act Density 0.034%

    No Known Activations