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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "drop" and its variations, often in contexts related to relinquishing or letting go of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ume
    -0.18
    iring
    -0.18
    leness
    -0.16
     Up
    -0.15
    ffects
    -0.15
    jury
    -0.15
    irl
    -0.14
    ifers
    -0.14
    ating
    -0.14
    Up
    -0.14
    POSITIVE LOGITS
     anchor
    0.31
    kick
    0.27
     trou
    0.27
     hints
    0.26
    anchor
    0.26
    -anchor
    0.24
    -down
    0.23
     dead
    0.23
     bombs
    0.22
    -off
    0.22
    Act Density 0.029%

    No Known Activations