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

    Neuronpedia

    INDEX
    Explanations

    empathetic and supportive phrases in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abox
    -0.17
    ONES
    -0.16
    oba
    -0.16
     Brad
    -0.15
    eways
    -0.15
    oupon
    -0.14
    engo
    -0.14
    Symbol
    -0.14
    ewed
    -0.14
     INS
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.18
     strength
    0.17
     anc
    0.15
    strength
    0.15
     eventually
    0.15
    iento
    0.15
     recovery
    0.14
    æ¼
    0.14
     soon
    0.14
    oloj
    0.14
    Act Density 0.167%

    No Known Activations