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

    Neuronpedia

    INDEX
    Explanations

    references to lists and their operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blessés
    -0.55
    haran
    -0.55
    simmon
    -0.55
    EndContext
    -0.53
    ctica
    -0.52
     naturelles
    -0.51
     défaut
    -0.50
     OMITBAD
    -0.50
    bari
    -0.49
    straint
    -0.49
    POSITIVE LOGITS
    push
    0.93
     push
    0.87
     pushed
    0.72
     pushes
    0.72
     append
    0.71
     pushing
    0.68
     Push
    0.67
     PUSH
    0.66
    append
    0.65
     Pushing
    0.64
    Act Density 0.107%

    No Known Activations