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

    Neuronpedia

    INDEX
    Explanations

    references to relationships or connections in various contexts

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

    relation to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     téc
    -0.40
     könny
    -0.37
    Choisissez
    -0.37
    ppchen
    -0.35
     sucked
    -0.35
     Cientí
    -0.34
     Nuestros
    -0.31
     fáciles
    -0.30
    ngine
    -0.30
    jugador
    -0.30
    POSITIVE LOGITS
     relation
    1.28
     relationship
    1.09
     Relation
    1.02
    relation
    1.00
    relationship
    0.97
     relating
    0.97
     RELATION
    0.96
     Relationship
    0.96
     relations
    0.92
    Relationship
    0.90
    Act Density 0.022%

    No Known Activations