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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "alike" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phere
    -0.19
    flare
    -0.18
     UIBar
    -0.17
    uito
    -0.16
    UIT
    -0.15
    ůl
    -0.15
    bles
    -0.15
    jem
    -0.15
    urge
    -0.14
    mite
    -0.14
    POSITIVE LOGITS
     alike
    0.16
    ewan
    0.15
    kowski
    0.15
    iid
    0.14
    isans
    0.14
    ingo
    0.14
     Chi
    0.13
    elden
    0.13
    aje
    0.13
    zeitig
    0.13
    Act Density 0.010%

    No Known Activations