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

    Neuronpedia

    INDEX
    Explanations

    instances of communication and the roles of individuals in conversations or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bronnen
    -0.76
    IndentedString
    -0.52
     према
    -0.50
    ability
    -0.49
    ijen
    -0.49
     Ability
    -0.49
    assertNull
    -0.47
     relativi
    -0.47
    liv
    -0.46
    ματος
    -0.45
    POSITIVE LOGITS
    ConstraintMaker
    0.98
     how
    0.97
     what
    0.82
     bluntly
    0.80
     sternly
    0.74
     why
    0.74
    InputBorder
    0.73
     verbally
    0.72
     politely
    0.72
     explicitly
    0.71
    Act Density 0.171%

    No Known Activations