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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opposition or objections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jména
    -0.77
     houſe
    -0.71
     florales
    -0.69
     placés
    -0.66
    nemo
    -0.65
    ERTY
    -0.64
     собі
    -0.62
     ſch
    -0.62
    談社
    -0.61
     âgées
    -0.61
    POSITIVE LOGITS
     Against
    2.22
    Against
    2.22
     against
    2.15
    against
    2.05
     AGAINST
    1.95
     gegen
    1.66
     contre
    1.46
     tegen
    1.38
     melawan
    1.26
     против
    1.23
    Act Density 0.077%

    No Known Activations