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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and questions related to decisions and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itou
    -0.15
    contres
    -0.14
    andr
    -0.14
     ----------------------------------------------------------------------------
    -0.14
    sofar
    -0.13
    cl
    -0.13
    èĥ¡
    -0.13
    tein
    -0.13
    eland
    -0.13
    omik
    -0.13
    POSITIVE LOGITS
     something
    0.23
     things
    0.22
    something
    0.22
     someone
    0.21
     somebody
    0.20
     Something
    0.20
    omething
    0.19
    someone
    0.19
    Something
    0.19
    æľī人
    0.18
    Act Density 0.220%

    No Known Activations