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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "exactly" and expressions of precision or similarity

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

    exactness or sameness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chaude
    -0.50
     considérable
    -0.39
     Others
    -0.38
    Others
    -0.38
     minor
    -0.37
     gruesa
    -0.37
     Ufer
    -0.37
    InputTagHelper
    -0.37
     compréhen
    -0.36
    úsqueda
    -0.36
    POSITIVE LOGITS
     EXACTLY
    0.81
    EXACT
    0.81
     exactly
    0.78
     EXACT
    0.77
    exact
    0.77
     exact
    0.76
    exactly
    0.75
    Exactly
    0.75
     Exactly
    0.74
    Exact
    0.71
    Act Density 0.041%

    No Known Activations