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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and comparisons between entities or situations

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

    especially when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestBed
    -0.41
    getMenuInflater
    -0.41
    Mun
    -0.38
     Poitiers
    -0.37
     Lev
    -0.37
     another
    -0.36
     however
    -0.36
     heisst
    -0.36
    pageId
    -0.36
    MigrationBuilder
    -0.36
    POSITIVE LOGITS
     المعيارى
    0.55
    Especially
    0.55
    featureID
    0.53
    DIPSETTING
    0.53
    particularly
    0.52
    ticularly
    0.51
     Particularly
    0.48
    尤其是
    0.48
     particularmente
    0.48
     particularly
    0.48
    Act Density 0.090%

    No Known Activations