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

    Neuronpedia

    INDEX
    Explanations

    mentions of connections or links between entities or events

    oai_token-act-pair · gpt-3.5-turbo

    discussions about various types of connections or links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.73
    sburg
    -0.69
     Zo
    -0.66
    otos
    -0.64
    stall
    -0.63
     stalls
    -0.58
    ardless
    -0.58
     dro
    -0.57
     nib
    -0.56
     flown
    -0.56
    POSITIVE LOGITS
     ties
    0.97
     links
    0.95
     connections
    0.88
     connecting
    0.87
     linking
    0.81
    links
    0.81
    tones
    0.81
     similarities
    0.76
    connected
    0.75
     connected
    0.75
    Act Density 0.056%

    No Known Activations