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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.73
    клопе
    -0.68
    seamnă
    -0.68
     noDo
    -0.65
    acquisto
    -0.65
     purpoſe
    -0.64
     itſelf
    -0.63
    odotus
    -0.63
     pleaſure
    -0.63
     myſelf
    -0.63
    POSITIVE LOGITS
     later
    0.57
     baada
    0.57
     Shortly
    0.56
     Later
    0.56
     nachdem
    0.56
     successivamente
    0.55
     after
    0.54
     após
    0.53
    addGap
    0.52
     Subsequently
    0.51
    Act Density 0.703%

    No Known Activations