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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and hiring contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    offers, hires, or grants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.70
    RTHOOK
    -0.67
    Viungo
    -0.60
    MigrationBuilder
    -0.56
     CreateTagHelper
    -0.54
    SequentialGroup
    -0.53
    IContainer
    -0.52
     <=",
    -0.51
     становника
    -0.51
     nakalista
    -0.51
    POSITIVE LOGITS
     køb
    0.36
     []:
    0.36
     sikkert
    0.35
     Kenntnis
    0.31
    httphttps
    0.30
    Története
    0.29
     onResponse
    0.29
     kommet
    0.29
     możliwe
    0.29
     løpet
    0.28
    Act Density 0.056%

    No Known Activations