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

    Neuronpedia

    INDEX
    Explanations

    words related to establishing connections or relationships

    oai_token-act-pair · gpt-3.5-turbo

    the word "connect" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wolf
    -0.66
    cember
    -0.66
    arcity
    -0.64
     Variety
    -0.64
    perty
    -0.63
     Leaves
    -0.63
    --+
    -0.63
    YING
    -0.62
     Lucia
    -0.62
    oeuv
    -0.60
    POSITIVE LOGITS
     connect
    1.14
     Connect
    1.10
    Connect
    1.06
    connect
    1.04
     dots
    1.02
     connects
    1.01
     connections
    0.99
    icut
    0.99
    ahime
    0.96
    connected
    0.91
    Act Density 0.014%

    No Known Activations