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

    Neuronpedia

    INDEX
    Explanations

    expressions related to generosity and kindness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to generosity and kindness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.83
    ulic
    -0.82
    aeda
    -0.77
    undown
    -0.76
    ulhu
    -0.76
    azeera
    -0.75
    Downloadha
    -0.74
    ahon
    -0.73
    ulz
    -0.72
    ilib
    -0.71
    POSITIVE LOGITS
     kindness
    1.08
    giving
    1.08
    hearted
    0.99
     gesture
    0.96
     gracious
    0.93
     toward
    0.90
     towards
    0.85
     gift
    0.82
     gifts
    0.82
     hosp
    0.81
    Act Density 0.139%

    No Known Activations