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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and activities involving physical movement

    oai_token-act-pair · gpt-3.5-turbo

    the use of commas in descriptive or complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģĸ
    -0.79
    è£ħ
    -0.79
     guiActiveUnfocused
    -0.77
    ļéĨĴ
    -0.74
    ãĥ¯
    -0.72
    pering
    -0.71
    advertising
    -0.69
    ãĤ´ãĥ³
    -0.69
    eele
    -0.65
    chell
    -0.65
    POSITIVE LOGITS
     however
    0.99
     but
    0.97
     albeit
    0.94
     though
    0.92
     yes
    0.91
     meanwhile
    0.83
     yeah
    0.77
     too
    0.77
     moreover
    0.76
     although
    0.76
    Act Density 0.438%

    No Known Activations