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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing intention or suggestion

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

    intentions or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.45
     poveznice
    -0.42
     lendemain
    -0.41
    quelize
    -0.40
     lenker
    -0.39
     Савезне
    -0.38
     gynhyrchwyd
    -0.38
    laş
    -0.37
     defaultstate
    -0.35
     voorbeeld
    -0.35
    POSITIVE LOGITS
    ########.
    0.47
    PreInfinity
    0.46
     minimum
    0.45
     bones
    0.44
    Motors
    0.44
    sistance
    0.43
     Taktlose
    0.42
     bone
    0.42
    出版年
    0.42
    EndProject
    0.41
    Act Density 0.073%

    No Known Activations