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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate familial relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.78
    NUMX
    -0.77
    脚注の使い方
    -0.76
     canst
    -0.73
    مقاله
    -0.72
     Signalez
    -0.72
     doubtnut
    -0.71
    AsUp
    -0.71
     purpoſe
    -0.70
     $_"
    -0.68
    POSITIVE LOGITS
     former
    0.60
     and
    0.58
     Tre
    0.57
     four
    0.52
    トレ
    0.51
     three
    0.51
     tre
    0.48
     six
    0.48
     
    0.48
     five
    0.47
    Act Density 0.017%

    No Known Activations