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

    Neuronpedia

    INDEX
    Explanations

    mentions of the action "contacted" in various contexts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.57
    Население
    -0.54
    मित
    -0.52
     presence
    -0.49
    AutoresizingMask
    -0.49
    牲
    -0.48
     rollen
    -0.47
     touch
    -0.47
    assign
    -0.47
     efectivo
    -0.46
    POSITIVE LOGITS
     contacted
    2.77
     contacting
    1.73
     approached
    1.23
     emailed
    1.09
     consulted
    0.97
     menghubungi
    0.92
     phoned
    0.92
    conta
    0.91
     Conta
    0.89
     contacter
    0.88
    Act Density 0.001%

    No Known Activations