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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating combinations or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pau
    -0.56
     institutional
    -0.53
     OP
    -0.52
     PS
    -0.51
     Mid
    -0.50
     trauma
    -0.50
     entertainment
    -0.49
     Tek
    -0.49
     lounge
    -0.48
     erst
    -0.48
    POSITIVE LOGITS
     Combinations
    0.78
     combinations
    0.77
    combination
    0.75
    combinations
    0.75
     combinaison
    0.74
    Combination
    0.74
     kombinasi
    0.72
     combinação
    0.70
     Kombination
    0.69
     combinatie
    0.66
    Act Density 0.243%

    No Known Activations