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

    Neuronpedia

    INDEX
    Explanations

    invitations to join something or participate in an activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases prompting participation or membership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disposed
    -0.82
     destro
    -0.82
    intendent
    -0.75
     conclud
    -0.71
     discharged
    -0.71
    otropic
    -0.67
     conflic
    -0.65
    iren
    -0.64
    ilogy
    -0.64
    orp
    -0.64
    POSITIVE LOGITS
     Join
    1.08
    Join
    1.04
    join
    0.92
    ATURES
    0.81
    joining
    0.77
    prises
    0.74
    âĸ¬âĸ¬
    0.74
    fleet
    0.74
     join
    0.72
    jen
    0.71
    Act Density 0.017%

    No Known Activations