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

    Neuronpedia

    INDEX
    Explanations

    words indicating uncertainty or qualifications in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.67
    Архівовано
    -0.64
    guantes
    -0.61
    ("/");
    -0.57
    pade
    -0.57
    DatabaseError
    -0.57
    ंदीखरीदारी
    -0.56
    ('/');
    -0.55
    SuppressMessage
    -0.55
     schme
    -0.54
    POSITIVE LOGITS
     esternos
    0.79
    ImageContext
    0.68
    oredCriteria
    0.63
    EndContext
    0.54
    ⓧ
    0.53
    stdc
    0.51
    posedge
    0.49
    principalTable
    0.49
    ANTLR
    0.49
    #+#
    0.48
    Act Density 0.705%

    No Known Activations