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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to empathy and social connections

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

    Follows "towards" or "for"

    np_acts-logits-general · gemini-2.0-flash

    towards people and ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.80
    FunctionFlags
    -0.77
     postIndex
    -0.71
     صوتيه
    -0.70
    الحياه
    -0.70
    $")
    -0.68
    AnimationsModule
    -0.66
    GenerationType
    -0.66
    Lambert
    -0.63
     betweenstory
    -0.62
    POSITIVE LOGITS
     objects
    0.55
     things
    0.54
    roën
    0.50
     Things
    0.48
    seeing
    0.48
    objects
    0.47
     seeing
    0.45
    ematica
    0.45
     lire
    0.45
     anything
    0.43
    Act Density 0.260%

    No Known Activations