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

    Neuronpedia

    INDEX
    Explanations

    terms indicating permission or facilitation within a process or exploration of features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.64
    amodel
    -0.54
     referenties
    -0.53
    ngdoc
    -0.53
    tellar
    -0.53
     ourselves
    -0.52
    äume
    -0.51
    ativité
    -0.51
     yourself
    -0.51
     myself
    -0.51
    POSITIVE LOGITS
     allowing
    1.87
     Allowing
    1.72
     enabling
    1.63
    allowing
    1.56
     permitting
    1.45
     requiring
    1.44
     permitiendo
    1.27
     forcing
    1.21
     Enabling
    1.20
     encouraging
    1.19
    Act Density 0.225%

    No Known Activations