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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of anticipation or eagerness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortex
    -0.15
    lette
    -0.14
    ropy
    -0.14
    ̣
    -0.14
    hoe
    -0.14
    erti
    -0.14
    apture
    -0.14
    allback
    -0.14
    ncy
    -0.13
    usp
    -0.13
    POSITIVE LOGITS
     wait
    0.24
     stress
    0.22
     WAIT
    0.21
     believe
    0.20
    wait
    0.20
     stresses
    0.19
     imagine
    0.19
    /wait
    0.18
     Stress
    0.18
     waits
    0.18
    Act Density 0.028%

    No Known Activations