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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and interaction between people

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "exchange."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Loading
    -0.85
    heid
    -0.83
    chair
    -0.79
    trump
    -0.76
    jet
    -0.75
    wing
    -0.74
    amina
    -0.73
    jam
    -0.71
    loop
    -0.70
    castle
    -0.70
    POSITIVE LOGITS
     glances
    0.93
     vows
    0.85
     pairs
    0.82
     litres
    0.73
    nil
    0.73
     between
    0.73
     roomm
    0.72
     letters
    0.70
    VALUE
    0.69
     favour
    0.68
    Act Density 0.064%

    No Known Activations