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

    Neuronpedia

    INDEX
    Explanations

    terminology related to restrictions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
     الرياضيه
    -0.57
     ujednoznacz
    -0.57
     ProtoMessage
    -0.54
    Vidite
    -0.52
    expandindo
    -0.50
    المناصب
    -0.50
     OMITTED
    -0.49
    oa̍t
    -0.48
     pinulongan
    -0.48
    POSITIVE LOGITS
     irreversible
    0.77
     irrevocable
    0.69
     inflexible
    0.60
     irre
    0.56
    irre
    0.55
     immovable
    0.55
     Immutable
    0.53
     immutable
    0.53
     readonly
    0.52
     immu
    0.51
    Act Density 0.993%

    No Known Activations