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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "joined" indicating a sense of affiliation or teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unknowns
    -0.53
    <table>
    -0.52
     wounds
    -0.51
    NoSuch
    -0.50
     Extr
    -0.50
     שכ
    -0.50
     matur
    -0.50
     keuken
    -0.50
     evapor
    -0.50
     Solu
    -0.49
    POSITIVE LOGITS
     joined
    1.74
     Joined
    1.69
    Joined
    1.63
    joined
    1.45
    Joining
    1.11
     attended
    1.11
     Joining
    1.08
     rejoined
    1.06
    attended
    0.96
    joining
    0.94
    Act Density 0.219%

    No Known Activations