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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collaboration or compliance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cooperation and collaborative action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fly
    -0.88
    nova
    -0.76
    ¥µ
    -0.75
    dream
    -0.72
    mort
    -0.72
    frey
    -0.72
    care
    -0.72
    scape
    -0.72
    senal
    -0.69
    blogspot
    -0.68
    POSITIVE LOGITS
     cooper
    1.15
     cooperating
    0.94
    atively
    0.86
    atives
    0.85
     cooperate
    0.84
     cooperative
    0.84
     arrang
    0.75
     juices
    0.70
     agreement
    0.68
     cooperation
    0.68
    Act Density 0.028%

    No Known Activations