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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inclusion or presence within groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tash
    -0.64
    ்கள்
    -0.64
     HPV
    -0.63
     Peshawar
    -0.63
     Othello
    -0.63
    R
    -0.61
    chec
    -0.59
    Ra
    -0.59
    L
    -0.57
    vbox
    -0.57
    POSITIVE LOGITS
     AMONG
    1.48
     Amongst
    1.44
     among
    1.36
     Among
    1.33
    among
    1.32
     amongst
    1.31
    Among
    1.16
     parmi
    1.05
    Среди
    0.98
     среди
    0.96
    Act Density 0.019%

    No Known Activations