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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the challenges of communication and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amat
    -0.16
     way
    -0.14
    cope
    -0.14
    yle
    -0.14
    ession
    -0.14
    ilog
    -0.14
     vaz
    -0.14
    wap
    -0.14
    AndWait
    -0.14
    aeda
    -0.13
    POSITIVE LOGITS
     enters
    0.26
     rubber
    0.24
     comes
    0.23
     really
    0.22
     begins
    0.22
     truly
    0.20
    Enter
    0.20
     becomes
    0.20
     enter
    0.20
     shines
    0.19
    Act Density 0.071%

    No Known Activations