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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate debate, questioning, or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaiter
    -0.75
    DockStyle
    -0.69
    脚注の使い方
    -0.69
    msgTypes
    -0.66
    ніципалі
    -0.66
    rrggbb
    -0.65
     préférence
    -0.64
    CppCodeGen
    -0.64
    AnchorStyles
    -0.63
     ainfi
    -0.62
    POSITIVE LOGITS
     reasons
    0.67
     discussion
    0.63
     political
    0.57
     technical
    0.57
     debatable
    0.55
     debate
    0.54
     Reasons
    0.52
     discussions
    0.52
     Suff
    0.51
     debates
    0.50
    Act Density 0.478%

    No Known Activations