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

    Neuronpedia

    INDEX
    Explanations

    Do note that the neuron 4 activates particularly when it encounters the word "quirk" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    words related to quirks or oddities, particularly in reference to people or behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hur
    -0.68
    rade
    -0.64
    iam
    -0.63
    amaz
    -0.62
    ÙĴ
    -0.62
    gang
    -0.62
    sword
    -0.60
    âĺħâĺħ
    -0.59
    ++++
    -0.59
     belt
    -0.59
    POSITIVE LOGITS
    conservancy
    0.87
    earance
    0.82
    enhagen
    0.81
    atcher
    0.78
    utic
    0.75
    adem
    0.73
    opsis
    0.69
    ensable
    0.69
    lihood
    0.67
     Cipher
    0.67
    Act Density 0.050%

    No Known Activations