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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing reciprocity or mutuality

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

    and vice versa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ciclop
    -0.31
     oeufs
    -0.31
    '])){
    -0.31
     sacerd
    -0.30
    XmlRootElement
    -0.30
    skal
    -0.29
    "",
    -0.29
     nakalista
    -0.29
     developer
    -0.29
    upaten
    -0.29
    POSITIVE LOGITS
     versa
    2.42
    versa
    1.38
     Versa
    1.24
    Vers
    0.97
     VERS
    0.92
     viceversa
    0.91
     Vers
    0.86
    VERS
    0.84
     vers
    0.81
    Conversely
    0.78
    Act Density 0.003%

    No Known Activations