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

    Neuronpedia

    INDEX
    Explanations

    instances where individuals or groups are joining something or someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "join" and its variations, indicating affiliations or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tiss
    -0.73
    framework
    -0.67
    bane
    -0.66
    binary
    -0.66
    intendent
    -0.65
    ester
    -0.65
    otropic
    -0.65
    rag
    -0.64
     tuber
    -0.63
    posal
    -0.63
    POSITIVE LOGITS
    lehem
    0.82
     forces
    0.80
     ranks
    0.69
    ATURES
    0.68
     Forces
    0.67
    ãĥĥ
    0.67
     Kens
    0.67
    TAIN
    0.66
    ters
    0.66
     chats
    0.65
    Act Density 0.032%

    No Known Activations