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

    Neuronpedia

    INDEX
    Explanations

    instances of disbelief or skepticism in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressions of disagreement or skepticism, particularly the phrase "I don't" at the beginning of sentences expressing doubt or contrary opinions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.55
     мәкал
    -0.50
    doria
    -0.47
     архивлан
    -0.46
    bootstrapcdn
    -0.46
    IsMutable
    -0.46
    Бахар
    -0.45
    日閲覧
    -0.44
    <?
    -0.44
    #+#
    -0.44
    POSITIVE LOGITS
     know
    0.83
    know
    0.63
     think
    0.60
     believe
    0.56
     blame
    0.52
     ever
    0.51
     weten
    0.50
     remember
    0.49
    Know
    0.48
     wiem
    0.47
    Act Density 0.115%

    No Known Activations