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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that express uncertainty or caution regarding future events

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

    Preceding qualifiers or intensifiers such as "too", "very", "only"

    np_acts-logits-general · gemini-2.0-flash

    too early

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.54
    Бахар
    -0.54
     Menon
    -0.54
     CreateTagHelper
    -0.51
     ongles
    -0.50
    Ikus
    -0.49
    escens
    -0.48
     laku
    -0.47
    └──
    -0.46
     filles
    -0.46
    POSITIVE LOGITS
     early
    1.75
    early
    1.53
    Early
    1.48
     Early
    1.45
     EARLY
    1.37
     preliminary
    1.18
    EARLY
    1.16
     premature
    1.11
     frühen
    1.07
    Preliminary
    0.99
    Act Density 0.147%

    No Known Activations