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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or confirmations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.68
    ρης
    -0.56
    drop
    -0.55
     nevoie
    -0.51
    נְ
    -0.50
     
    -0.50
     насеље
    -0.50
     Mau
    -0.49
     Ode
    -0.49
     Sen
    -0.49
    POSITIVE LOGITS
     itſelf
    0.93
    tahui
    0.87
    NOPQRST
    0.83
    };*/
    0.80
     Chwiliwch
    0.78
    ScopeManager
    0.76
     Jefus
    0.74
    Rhestr
    0.73
     himſelf
    0.73
    WriteTagHelper
    0.73
    Act Density 0.000%

    No Known Activations