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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their usage in relation to actions or states

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ORTS
    -0.53
     the
    -0.51
     more
    -0.50
    shutil
    -0.46
     most
    -0.45
    gın
    -0.44
     successfully
    -0.42
     Herzens
    -0.41
     its
    -0.41
     it
    -0.41
    POSITIVE LOGITS
    TargetException
    0.88
     Савезне
    0.85
    posedge
    0.84
    UserScript
    0.84
     Majefty
    0.82
    WireFormatLite
    0.81
    sidemargin
    0.80
    saraba
    0.78
    findpost
    0.78
    IndentedString
    0.78
    Act Density 0.216%

    No Known Activations