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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating uncertainty or questioning the status quo

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scriptcase
    -0.71
    CPtr
    -0.66
     invokingState
    -0.60
    TypedDataSet
    -0.59
    どうやら
    -0.56
    Portail
    -0.55
    nikami
    -0.54
    AndEndTag
    -0.53
    ญิง
    -0.51
     undisclosed
    -0.51
    POSITIVE LOGITS
     imagine
    1.58
     Imagine
    1.40
    Imagine
    1.35
    imagine
    1.30
     think
    1.18
     look
    1.10
    Think
    1.08
     Think
    1.07
     Look
    1.05
     Suppose
    1.02
    Act Density 0.450%

    No Known Activations