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

    Neuronpedia

    INDEX
    Explanations

    references to joining or participating in activities or groups

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     joint
    -1.21
     Joint
    -0.99
    Joint
    -0.98
    joint
    -0.96
     JOINT
    -0.82
    JOINT
    -0.75
     joints
    -0.61
     jointly
    -0.59
    join
    -0.53
     adev
    -0.52
    POSITIVE LOGITS
     joining
    1.90
     Joining
    1.73
    Joining
    1.67
    joining
    1.36
    الإنجليزية
    0.97
     CreateTagHelper
    0.81
     IBOutlet
    0.77
     propOrder
    0.75
    ksikon
    0.72
    ValueStyle
    0.72
    Act Density 0.003%

    No Known Activations