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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and expressions indicating alternatives or choices

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.78
     mergeFrom
    -0.77
    pyplot
    -0.74
    RepeatedField
    -0.70
     estekak
    -0.69
    tableFuture
    -0.66
    GEBURTSDATUM
    -0.66
    uffff
    -0.60
     nahilalakip
    -0.59
    Geplaatst
    -0.57
    POSITIVE LOGITS
    SBATCH
    0.56
    esModule
    0.49
    genie
    0.46
    NameValuePair
    0.45
     bersama
    0.44
    StartTag
    0.44
    امة
    0.44
    phor
    0.43
    tamment
    0.43
     onCreate
    0.42
    Act Density 0.007%

    No Known Activations