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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opposition or resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jména
    -0.81
    談社
    -0.77
     houſe
    -0.75
    ERTY
    -0.70
     placés
    -0.66
     âgées
    -0.64
     собі
    -0.63
    Txn
    -0.63
     pensato
    -0.62
    nemo
    -0.61
    POSITIVE LOGITS
    Against
    1.74
     Against
    1.73
     against
    1.57
     AGAINST
    1.52
    against
    1.49
     gegen
    1.32
     contre
    1.18
     tegen
    1.04
     melawan
    0.97
    SuppressMessage
    0.95
    Act Density 0.074%

    No Known Activations