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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal preferences and suitability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    səhifə
    -0.56
     queſta
    -0.54
    enterOuterAlt
    -0.54
     propOrder
    -0.50
    رشف
    -0.49
     gynnwys
    -0.49
     judiciaire
    -0.49
     ſche
    -0.48
     itſelf
    -0.48
     Biôgrafia
    -0.47
    POSITIVE LOGITS
     suited
    0.82
    suited
    0.73
     cocok
    0.71
    適合
    0.69
     suitability
    0.66
     suit
    0.66
    适合
    0.65
     suits
    0.65
     unsuitable
    0.60
     appropriateness
    0.58
    Act Density 0.291%

    No Known Activations