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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look" and its variations in different forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    92
    -0.15
    94
    -0.14
    BITS
    -0.14
     dane
    -0.14
    ément
    -0.14
    ardy
    -0.14
     вÑĭглÑıд
    -0.14
    iom
    -0.14
    93
    -0.13
    avig
    -0.13
    POSITIVE LOGITS
     closely
    0.34
     at
    0.29
     closer
    0.27
     Clo
    0.24
    Clo
    0.23
     carefully
    0.22
     clos
    0.22
     deeper
    0.20
     CLOSE
    0.20
    clo
    0.20
    Act Density 0.040%

    No Known Activations