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

    Neuronpedia

    INDEX
    Explanations

    numerical values and data references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.58
     
    -0.55
    addPreferredGap
    -0.54
    ResumeLayout
    -0.53
     useDispatch
    -0.51
    antMatchers
    -0.50
    ,
    -0.49
      
    -0.47
     in
    -0.46
    SuppressLint
    -0.46
    POSITIVE LOGITS
     Majefty
    0.95
     raiſ
    0.94
     myſelf
    0.94
     ―――――
    0.91
     poffe
    0.88
     Efq
    0.88
     ſche
    0.81
     itſelf
    0.81
     Anſ
    0.77
     Theſe
    0.77
    Act Density 0.125%

    No Known Activations