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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and their relationships within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.72
     canceled
    -0.68
     colorless
    -0.68
    fillType
    -0.68
    djangoproject
    -0.67
    URLException
    -0.67
     grayish
    -0.67
    Παραπομπές
    -0.65
     Ее
    -0.64
    Colorful
    -0.62
    POSITIVE LOGITS
     centres
    0.62
     organisations
    0.59
     mould
    0.56
     utilisation
    0.56
     humour
    0.55
     enquiries
    0.54
     behaviour
    0.54
     utilising
    0.53
    initialise
    0.53
     Mould
    0.53
    Act Density 0.116%

    No Known Activations