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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal anecdotes or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DIRECTION
    -0.61
    Děkuji
    -0.55
     resultMap
    -0.54
    horabuena
    -0.53
    amaha
    -0.53
     provisoire
    -0.53
    appartamento
    -0.52
     béné
    -0.51
     håll
    -0.51
     ComVisible
    -0.51
    POSITIVE LOGITS
     incidents
    0.84
     incident
    0.76
     happened
    0.76
    happened
    0.74
     anecdote
    0.72
     episodi
    0.68
     Incidents
    0.68
     recounted
    0.67
     anecdotes
    0.65
    エピソード
    0.64
    Act Density 0.391%

    No Known Activations