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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing interpersonal relationships and emotional connections

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

    make someone feel or do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saites
    -0.52
     bajas
    -0.44
     gewisser
    -0.44
     demás
    -0.42
     vecind
    -0.41
     aliento
    -0.41
    colección
    -0.41
     macetas
    -0.41
     kolej
    -0.40
     habido
    -0.40
    POSITIVE LOGITS
     make
    0.90
    Made
    0.86
     Make
    0.85
    make
    0.84
    Make
    0.83
     MAKE
    0.83
    MADE
    0.82
     Made
    0.80
    MAKE
    0.78
     Making
    0.77
    Act Density 0.035%

    No Known Activations