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

    Neuronpedia

    INDEX
    Explanations

    invitations or prompts to join community-related activities

    oai_token-act-pair · gpt-3.5-turbo

    invitations to join groups or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.82
     tiss
    -0.70
     disposed
    -0.67
    bane
    -0.66
     earthqu
    -0.64
     tuber
    -0.63
    borgh
    -0.63
    otropic
    -0.63
    intendent
    -0.62
    inarily
    -0.62
    POSITIVE LOGITS
    Join
    1.00
     Join
    0.94
    join
    0.85
    ATURES
    0.82
    âĸ¬âĸ¬
    0.78
    fleet
    0.76
    hold
    0.76
     join
    0.76
    hips
    0.74
    ãĥĥ
    0.72
    Act Density 0.020%

    No Known Activations