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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opposition or confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jména
    -0.73
    ERTY
    -0.71
     houſe
    -0.69
    nemo
    -0.68
    談社
    -0.64
     bezeichneter
    -0.64
     florales
    -0.63
    Txn
    -0.62
     собі
    -0.61
     placés
    -0.61
    POSITIVE LOGITS
    Against
    1.92
     Against
    1.91
     against
    1.80
    against
    1.73
     AGAINST
    1.72
     gegen
    1.39
     contre
    1.30
     tegen
    1.23
     melawan
    1.08
     против
    1.05
    Act Density 0.087%

    No Known Activations