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

    Neuronpedia

    INDEX
    Explanations

    structured transitions and indications of sequence in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sih
    -0.51
    leyeb
    -0.46
     or
    -0.41
    этому
    -0.41
     számára
    -0.40
    lagos
    -0.40
     beberapa
    -0.40
     haar
    -0.39
     daardoor
    -0.39
    Παραπομπές
    -0.38
    POSITIVE LOGITS
     secondly
    1.46
    Secondly
    1.44
     Secondly
    1.44
     Thirdly
    1.25
     Lastly
    1.24
    Lastly
    1.23
    первых
    1.13
     Firstly
    1.11
    Firstly
    1.11
     lastly
    1.09
    Act Density 0.204%

    No Known Activations