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

    Neuronpedia

    INDEX
    Explanations

    statements or claims about various topics that are framed as significant or noteworthy events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illance
    -0.18
    åĬ
    -0.15
    entar
    -0.15
    oho
    -0.15
    ÙĩÙĨ
    -0.14
    ibilidade
    -0.14
    ãģĸ
    -0.14
    adÃŃ
    -0.14
     terminating
    -0.13
     Möglich
    -0.13
    POSITIVE LOGITS
     happening
    0.17
     happen
    0.16
     true
    0.16
    ÙĪÙĦÙĬÙĪ
    0.16
     Happ
    0.15
     remarkable
    0.15
    426
    0.15
    è¾ĵ
    0.15
    ory
    0.14
    riott
    0.14
    Act Density 0.020%

    No Known Activations