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

    Neuronpedia

    INDEX
    Explanations

    words related to changes, particularly in regard to transitions or shifts in context or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enfance
    -0.53
     tenuta
    -0.51
     hjemme
    -0.51
     ritratto
    -0.49
    ソリン
    -0.48
     riun
    -0.47
     témoins
    -0.47
    ølge
    -0.47
     memeriksa
    -0.47
    écnicas
    -0.46
    POSITIVE LOGITS
     shift
    1.12
     switch
    1.10
     shifted
    1.03
     shifting
    1.00
     Shifting
    0.98
     Switch
    0.95
     shifts
    0.94
     Shift
    0.94
    shift
    0.93
     switched
    0.93
    Act Density 0.512%

    No Known Activations